CN111193642A

CN111193642A - Pressure measurement method, pressure measurement platform, electronic device and readable storage medium

Info

Publication number: CN111193642A
Application number: CN201911397207.6A
Authority: CN
Inventors: 江绍宇
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2019-12-30
Filing date: 2019-12-30
Publication date: 2020-05-22

Abstract

The embodiment of the specification discloses a pressure measurement method, which is applied to a pressure sending server cluster and used for receiving configuration parameters sent by a pressure measurement system; determining the pressure sending parameters of each pressure sending server in the pressure sending server cluster according to the configuration parameters; each pressure sending server sends a pressure measurement request to a corresponding measured server in the measured server cluster according to the pressure sending parameters of the pressure sending server; each pressure sending server receives a request result returned by the corresponding tested server, wherein for each pressure sending server, the pressure sending server compresses all the received request results every set time length to obtain a compression request result of the pressure sending server, and the pressure sending server sends the compression request result of the pressure sending server to the pressure testing system, so that the pressure testing system receives the compression request result sent by each pressure sending server.

Description

Pressure measurement method, pressure measurement platform, electronic device and readable storage medium

Technical Field

The embodiment of the specification relates to the technical field of data processing, in particular to a pressure measurement method, a pressure measurement platform, electronic equipment and a readable storage medium.

Background

With the rapid development of internet technology, the requirements for the performance and stability of a server are higher and higher, and therefore, the server is often required to be subjected to pressure testing, and the performance indexes of the server and the processing speed condition of a network request are acquired, so that the stability of the server is ensured.

Currently, the step of performing pressure measurement on a server includes: determining configuration parameters of a pressure measurement task; and then, sending a pressure measurement request to the tested server cluster by a pressure server in the pressure server cluster according to the configuration parameters, wherein each pressure measurement request generates a request result and returns the request result to the pressure server cluster, and then the pressure server cluster returns to the pressure measurement platform for data analysis to obtain a pressure measurement report. However, as the traffic volume increases rapidly, the scale of the corresponding pressure sending cluster also needs to increase rapidly to perform a pressure measurement request for truly simulating the rapid increase of the traffic volume, and at this time, due to the increase of the total volume of the pressure sending server cluster, the total volume of the request results required to be sent is increased rapidly, so that the transmitted data volume is increased rapidly.

Disclosure of Invention

The embodiment of the specification provides a pressure measurement method, a mobile terminal, an electronic device and a readable storage medium, which can effectively reduce the data volume of pressure measurement data uploading and reduce the times of pressure measurement data uploading.

A first aspect of an embodiment of the present specification provides a pressure measurement method, which is applied to a pressure sending server cluster, and includes:

receiving configuration parameters sent by a pressure measurement system, wherein the configuration parameters are parameters for configuring a pressure measurement task;

determining the pressure sending parameters of each pressure sending server in the pressure sending server cluster according to the configuration parameters;

each pressure sending server sends a pressure measurement request to a corresponding measured server in the measured server cluster according to the pressure sending parameters of the pressure sending server;

each pressure sending server receives a request result returned by the corresponding tested server, wherein for each pressure sending server, the pressure sending server compresses all the received request results every set time length to obtain a compression request result of the pressure sending server, and the pressure sending server sends the compression request result of the pressure sending server to the pressure testing system, so that the pressure testing system receives the compression request result sent by each pressure sending server.

A second aspect of the embodiments of the present specification provides a method for analyzing pressure measurement data, which is applied to a pressure measurement system, and includes:

acquiring configuration parameters of a pressure measurement task, and sending the configuration parameters to a pressure sending server cluster;

receiving a compression request result sent by each pressure sending server in the pressure sending server cluster, wherein each compression request result is obtained by compressing all received request results every set time length by the corresponding pressure sending server;

performing data analysis on all the received compression request results by using an HdrHistopram algorithm to obtain analysis results;

and obtaining the pressure measurement report according to the analysis result.

The third aspect of the embodiments of the present specification further provides a pressure measurement apparatus, including:

the configuration parameter receiving unit is used for receiving configuration parameters sent by the pressure measurement system, wherein the configuration parameters are parameters for configuring a pressure measurement task;

the pressure sending parameter determining unit is used for determining the pressure sending parameter of each pressure sending server in the pressure sending server cluster according to the configuration parameter;

the pressure measurement request sending unit is used for sending a pressure measurement request to a corresponding server to be measured in the server cluster to be measured by each pressure sending server according to the pressure sending parameter of the pressure sending server;

the request result receiving unit is used for receiving the request result returned by the corresponding tested server by each pressure sending server;

and the request result compressing and sending unit is used for compressing all received request results every set time interval by the pressure sending server aiming at each pressure sending server to obtain the compression request result of the pressure sending server, and the pressure sending server sends the compression request result of the pressure sending server to the pressure measurement system so that the pressure measurement system receives the compression request result sent by each pressure sending server.

The fourth aspect of the embodiments of the present specification further provides a pressure measurement data analysis device, including:

the configuration parameter acquisition and sending unit is used for acquiring configuration parameters of the pressure measurement task and sending the configuration parameters to the pressure sending server cluster;

a compression request result receiving unit, configured to receive a compression request result sent by each pressure server in the pressure server cluster, where each compression request result is obtained by compressing all received request results every set time interval by the corresponding pressure server;

the data analysis unit is used for carrying out data analysis on the received compression request results by using an HdrHistopram algorithm to obtain analysis results;

and the pressure measurement report acquisition unit is used for acquiring the pressure measurement report according to the analysis result.

The fifth aspect of the embodiments of the present specification further provides a pressure measurement platform, which includes a pressure measurement system, a pressure sending server cluster and a measured server cluster, and includes:

the pressure measurement system is used for acquiring configuration parameters of a pressure measurement task and sending the configuration parameters to the pressure sending server cluster;

the pressure sending server cluster is used for each pressure sending server in the pressure sending server cluster to obtain the configuration parameters; determining the pressure sending parameters of each pressure sending server according to the configuration parameters; each pressure sending server sends a pressure measurement request to a corresponding server to be measured in the server cluster to be measured according to the pressure sending parameter of the pressure sending server;

the server cluster under test is used for responding the received pressure measurement request and generating a corresponding request result after each server under test in the server cluster under test receives the pressure measurement request of the corresponding pressure sending server, and each server under test returns the request result generated by the server under test to the pressure sending server cluster;

the pressure server cluster is used for each pressure server in the pressure server cluster to receive a request result returned by a corresponding tested server, wherein for each pressure server, the pressure server compresses all the received request results at intervals of set time to obtain a compression request result of the pressure server, and the pressure server sends the compression request result of the pressure server to the pressure testing system;

and the pressure measurement system is used for receiving the compression request results sent by each pressure sending server and analyzing the data of all the received compression request results to obtain a pressure measurement report.

The sixth aspect of the embodiments of the present specification further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the pressure measurement method and the pressure measurement data analysis method when executing the program.

The seventh aspect of the embodiments of the present specification further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the steps of the above-mentioned pressure measurement method and pressure measurement data analysis method.

The beneficial effects of the embodiment of the specification are as follows:

based on the technical scheme, each pressure server compresses all the request results obtained every set time length, and further obtains one compression request result, so that only one compression request result is uploaded to a pressure measurement system within the set time length, and multiple pressure measurement requests usually exist within the set time length, and only one compression request result is uploaded, namely, multiple pressure measurement requests exist within the set time length, and only one request result is uploaded, in the prior art, the request result corresponding to each obtained pressure measurement request needs to be uploaded once, and only one compression request result needs to be uploaded once within the set time length, so that the uploading times of each pressure server every set time length are reduced, and when the compression request result is formed by compressing multiple request results, compared with the result of multiple requests uploaded, the data volume uploaded by the method is reduced, the data volume uploaded can be effectively reduced, and the uploading frequency is reduced.

Drawings

FIG. 1 is a diagram illustrating a system architecture of a pressure measurement platform according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of a method of pressure measurement in an embodiment of the present disclosure;

FIG. 3 is a flow chart of a method of analyzing pressure measurement data according to an embodiment of the present disclosure;

FIG. 4 is a schematic structural diagram of a pressure device in an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of an analysis apparatus for pressure measurement data according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an electronic device in an embodiment of this specification.

Detailed Description

In order to better understand the technical solutions, the technical solutions of the embodiments of the present specification are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and are not limitations of the technical solutions of the present specification, and the technical features of the embodiments and embodiments of the present specification may be combined with each other without conflict.

In the embodiment of the present specification, Remote Direct Memory Access (RDMA for short) is generated to solve a delay of server-side data processing in network transmission; RDMA transfers data directly to a computer's storage area over a network, quickly moving data from one system to a remote system memory without any impact on the operating system, thus eliminating the need for as many computer processing functions as are needed. It eliminates the overhead of external memory copy and context switch, thus freeing up memory bandwidth and CPU cycles for improved application system performance.

In embodiments of the present specification, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In a first aspect, as shown in fig. 1, an embodiment of the present specification provides a pressure measurement platform, which includes a pressure measurement system 100, a pressure sending server cluster 200, and a measured server cluster 300, and includes:

the pressure measurement system 100 is used for acquiring configuration parameters of a pressure measurement task and sending the configuration parameters to the pressure sending server cluster 200;

the pressure server cluster 200 is used for each pressure server in the pressure server cluster 200 to acquire the configuration parameters; determining the pressure parameters of each pressure server according to the configuration parameters, and sending a pressure measurement request to the corresponding measured server in the measured server cluster 300 by each pressure server according to the pressure parameters of the pressure server;

the server cluster 300 under test is used for each server under test in the server cluster 300 under test to respond to the received pressure measurement request and generate a corresponding request result after receiving the pressure measurement request of the corresponding pressure sending server, and each server under test returns the request result generated by itself to the pressure sending server cluster 200;

the pressure sending server cluster 200 is used for each pressure sending server in the pressure sending server cluster 200 receiving a request result returned by a corresponding server to be tested, wherein for each pressure sending server, the pressure sending server compresses all the received request results at intervals of a set time length to obtain a compression request result of the pressure sending server, and the pressure sending server sends the compression request result of the pressure sending server to the pressure testing system 100;

and the pressure measurement system 100 is configured to receive the compression request result sent by each pressure sending server, and perform data analysis on all the received compression request results to obtain a pressure measurement report.

In the embodiment of the present disclosure, the pressure measurement system 100 may include, but is not limited to, a terminal mode, and may also be a system using a terminal and server mode. Specifically, in the embodiment of the present disclosure, the terminal may include a physical device of a type such as a smart phone, a desktop computer, a tablet computer, a notebook computer, a digital assistant, and a smart wearable device, and may also include software running in the physical device. The operating system running on the pressure measurement system 100 in the embodiment of the present specification may include, but is not limited to, an android system, an IOS system, linux, windows, and the like. The server may comprise a server operating independently, or a distributed server, or a server cluster consisting of a plurality of servers.

In addition, before the pressure measurement system 100 provides the pressure measurement service, initialization is performed, and an available pressure sending server is configured at the time of initialization. Specifically, the pressure server may send a registration message (the registration message includes the area information and the network protocol IP address information of the pressure server) to the pressure measurement system 100 for registration, and report the area information and the network protocol IP address information of the pressure server during registration. After receiving the registration message of the pressure server, the pressure measurement system 100 may add the pressure server to the pressure server cluster 200, record the area information and the IP address information of the pressure server, and complete registration. Therefore, subsequently, when the pressure test is required to be carried out on the tested server, a test instruction (a pressure test task is issued) can be sent to the corresponding pressure sending server, and the pressure test on the tested server is realized.

In this embodiment, the pressure measurement system 100 is connected to each pressure sending server in the pressure sending server cluster 200, and the pressure measurement system 100 receives a pressure measurement task created by a user, receives a configuration parameter corresponding to the pressure measurement task and input by the user, and then sends the configuration parameter to the pressure sending server cluster 200.

In this embodiment of the present specification, the pressure measurement system 100 first obtains a creation instruction for creating a pressure measurement task by a user, obtains the pressure measurement task, then obtains parameters input by the user for configuring the pressure measurement task, and obtains the configuration parameters; after the configuration parameters are obtained, the configuration parameters and the pressure sending environment are detected, then the pressure sending parameters of each pressure sending server are determined according to the configuration parameters, the pressure sending parameters are sent to each pressure sending server in the pressure sending server cluster 200 through instruction scheduling, each pressure sending server receives the pressure sending parameters, each pressure sending server generates a pressure testing request according to the pressure sending parameters, each pressure sending server sends the pressure testing request generated by the pressure sending server to the corresponding tested server in the tested server cluster 300, and each tested server in the tested server cluster 300 receives the pressure testing request.

In the embodiment of the present specification, if there is no prefix in "each of the transmitting servers", it indicates that "each of the transmitting servers" is each of the transmitting servers in the transmitting server cluster 200; and there is no prefix in "each server under test" described in the embodiments of the present specification, it indicates that "each server under test" is each server under test in the server cluster 300 under test.

In the embodiment of the present specification, the pressure-sending server cluster 200 is specifically a machine pool maintained by the pressure measurement platform side, that is, a server cluster that sends a request in the pressure measurement process; accordingly, the tested server cluster 300 is specifically a machine pool maintained by the service side and providing services to the outside, that is, a server cluster receiving a request in the pressure measurement process.

In this embodiment of the present disclosure, the configuration parameter may be a parameter based on a concurrent mode (virtual user mode), or may be a parameter based on a request Per Second (Requests Per Second, abbreviated as RPS) mode. When the configuration parameters are based on the concurrent mode, the configuration parameters include parameters such as the total number of virtual concurrent users and the pressure measurement duration, and at this time, the configuration parameters may include, for example, the total number of virtual concurrent users is 200 ten thousand and the pressure measurement duration is 60 seconds; and when the configuration parameters are based on the RPS mode, the configuration parameters include parameters such as the total RPS number and the pressure measurement duration, and at this time, the configuration parameters may include, for example, the total RPS number of 100 ten thousand times and the pressure measurement duration of 20 seconds.

Of course, the configuration parameters usually include data such as a configuration target magnitude, a pressure source, a pressure measurement duration, and an IP extension, which are only examples of the configuration parameters including the configuration target magnitude and the pressure measurement duration.

In this embodiment of the present specification, after the configuration parameters are obtained, the voltage sending parameters of each voltage sending server may be determined according to the configuration parameters; of course, the voltage sending parameter of each voltage sending server may also be determined according to the configuration parameter and the total number of voltage sending servers in the voltage sending server cluster 200, where, when the configuration parameter is based on the concurrency mode, the voltage sending parameter of each voltage sending server may include the number of concurrent users and the voltage measurement duration of the voltage sending server; accordingly, when the configuration parameters are based on the RPS mode, the pressure parameters of each pressure server may include the number of requests per second and the pressure measurement time length of the pressure server, and the description is not particularly limited.

In this embodiment, the sending server may be a desktop computer, a notebook computer, an all-in-one machine, a smart phone, or the like; correspondingly, the tested server can be a desktop computer, a notebook computer, an all-in-one machine, a smart phone and other equipment; the pressure server cluster 200 includes 2 and more than 2 pressure servers, and the tested server cluster 300 includes 2 and more than 2 tested servers, which is not limited in this specification.

In this embodiment of the present specification, each of the pressure servers in the pressure server cluster 200 corresponds to one or more tested servers in the tested server cluster 300, and each tested server corresponds to one pressure server, that is, one pressure server may correspond to one tested server, or may correspond to a plurality of tested servers, where the plurality means 2 or more than 2.

For example, if the servers to be tested in the server cluster 300 are b1, b2, b3, b4, b5 and b6, the a1 corresponds to b1, the a2 corresponds to b2, the a3 corresponds to b3, the a4 corresponds to b4, the a5 corresponds to b5, and the a6 corresponds to b6, with the transmitting servers in the transmitting server cluster 200 being a1, a2, a3, a4, a5 and a 6; if the servers to be tested in the server cluster 300 to be tested are b1, b2, b3, b4, b5, b6 and b7, then a1 corresponds to b1, a2 corresponds to b2, a3 corresponds to b3, a4 corresponds to b4, a5 corresponds to b5, and a6 corresponds to b6 and b 7. Therefore, one pressure sending server can correspond to one or more tested servers, and each tested server corresponds to one pressure sending server.

In this embodiment of the present specification, for each measured server in the measured server cluster 300, after receiving the pressure measurement request each time, the measured server responds to the pressure measurement request and generates a corresponding request result, and then returns the generated request result to the corresponding pressure-sending server.

For example, taking a pressure server as a2 and a server to be tested as b2, and the pressure request is an access request as an example, b2 responds to the access request after receiving the access request of the accessing user c1 sent by a2 at a certain time, and obtains the user information of c1, and at this time, the request result is the user information of c1, and the user information of c1 is returned to a 2; after receiving the access request of the access user c2 sent by the access user c2 at the next time b2, b2 responds to the access request of the access user c2, acquires the user information of c2, and returns the user information of c2 to the access user a2 as the request result of the access request, so that the request result obtained by responding to the access request is returned to the access user a2 after the access request is received by the access user b2 each time; and executing the operation aiming at each tested server, so that each pressure sending server can receive the sent pressure test request and return a request result.

In this embodiment of the present specification, each pressure sending server sends its own compression request result to the pressure measurement system 100, and the pressure measurement system 100 analyzes the compression request result of each pressure sending server and then performs data analysis using a data analysis model, where the data analysis model may be preset, the data analysis model is used to measure performance parameters of system performance indexes, the performance parameters may include, for example, transaction processing amount per second TPS of the system, response time RT, throughput, and number of concurrency, and the performance parameters may be set according to actual needs or may be set by a user or the system, and this specification is not limited specifically.

In this embodiment of the present specification, the set time duration may be set by a user or the pressure measurement system 100, or may be set according to an actual requirement, where the set time duration may be a fixed time duration or a variable time duration, and if the set time duration is the fixed time duration, the set time duration may be a fixed value such as 1 second(s), 2s, 3s, and 5 s; if the set time length is a variable time length, the set time length can be varied within 1s to 3s or within 2s to 5s, and the like, and if the set time length is varied within 1s to 3s, the value of the set time length can be varied with time, and the value of the set time length is changed accordingly, for example, the set time length can be 1s when the set time length is 10 months, 15 days, 15 minutes and 15 seconds (10:15:15:15), and the set time length can be 2s when the set time length is 10:15:15:16 s; the set time period may be 3s at 10:15:15:18s, etc.

Specifically, for each of the pressure servers, based on the analysis index of the data analysis model, the pressure server may compress all the received request results every set time period to obtain the compression request result of the pressure server.

Specifically, if the analysis index includes: total number of requests per second, time consumed per second; for total number of requests per second: if there are 5 requests in 1 second, the first field in the 5 requests is time (actual scene is timestamp), and the second field is time consumption (unit of millisecond) of a single request, where the 5 requests are specifically 2019090920: 40:30,1, 2019090920: 40:30,2, 2019090920: 40:30,2, 2019090920: 40:30,1, 2019090920: 40:30,3, for example 2019090920: 40:30,1, the request represents that 20 o' clock 40 min 30 s in 09 month in 2019 and the time consumption of the request is 1 millisecond, and then the 5 requests are compressed to obtain the result of 2019090920: 40:30,5 (the second has 5 requests, so the total number of requests is 5), and 9 (the total time consumption of the second request is 1+2+2+1+3, so the total time consumption of the request is 9 milliseconds).

In this embodiment of the present specification, if the analysis indicator includes a request time consumption, for each pressure server, the pressure server may compress all received request results every set time interval according to the analysis indicator to obtain a compression request result of the pressure server, where the compression request result includes an actual value of the request time consumption and an occurrence frequency.

Specifically, for each compression request result, if the compression request result is obtained by compressing N request results, N request elapsed times included in the N request results are obtained, and the N request elapsed times are compressed according to the number of occurrences of the request elapsed times having the same actual value in the N request elapsed times, so that the compression request result includes the request elapsed time and the number of occurrences thereof, where N is an integer not less than 2.

Specifically, in the process of compressing the N request elapsed times, the request elapsed times may be compressed into a format of K: V, where K represents the request elapsed times and V represents the number of times that the request elapsed times occur.

For example, also taking the 5 requests as an example, since the request time consumption in the 5 requests is sequentially 1, 2, 1 and 3, it can be seen that the number of occurrences of the request time consumption of 1 millisecond is 2, the number of occurrences of the request time consumption of 2 milliseconds is 2, and the number of occurrences of the request time consumption of 3s is 1, the 5 requests are compressed, and the obtained compression request results are 2019090920: 40:30,5, 1:2|2:2|3:1, where 1:2|2:2|3:1 represents that the number of occurrences of the request time consumption of 1 millisecond is 2, the number of occurrences of the request time consumption of 2 milliseconds is 2, and the number of occurrences of the request time consumption of 3s is 1.

In this way, each sending server will obtain one compressing request result by compressing every set time length, so that only one of the compression request results needs to be uploaded to the pressure measurement system 100 within the set time period, while there are typically multiple pressure measurement requests within the set duration and only one of the compression request results need be uploaded, that is, there are multiple pressure measurement requests in the set time length and only need to upload once, but in the prior art, the request result corresponding to each obtained pressure measurement request needs to be uploaded once, if there are multiple pressure measurement requests in the set time length and the number of uploading times corresponding to the multiple pressure measurement requests is the same as the number of requests of the multiple pressure measurement requests, in the embodiment of the present specification, each of the pressure servers only needs to upload one time within the set time length, so that the number of times that each of the pressure servers uploads every other set time length is reduced.

In addition, the pressure server cluster 200 includes a plurality of pressure servers, and under the condition that the number of times of transmission of each pressure server every other set time length is reduced, the number of times of transmission of each pressure server cluster 200 every other set time length is reduced by times, so that the data volume of data transmission can be greatly reduced; under the condition that the transmission times and the transmitted data volume are reduced, the loads of the collector and the transmission equipment for collecting the compression request result can be reduced, the number of the collectors and the transmission equipment which need to be newly added is reduced, and the cost can be effectively reduced during capacity expansion.

In this embodiment of the present specification, for each pressure server, according to an analysis index of the data analysis model, the pressure server compresses all received request results every set time duration, and after obtaining a compression request result of the pressure server, the pressure server performs format conversion on a compression request result of the pressure server to obtain a target compression request result of the pressure server, where a data format in the target compression request result conforms to the set format, so that each pressure server returns the target compression request result of the pressure server to the pressure measurement system 100 every set time duration, and the pressure measurement system 100 receives the target compression request result sent by each pressure server and then performs data analysis.

Specifically, when the format of the compression request result is converted, the format converter arranged in each pressure server can perform format conversion, so that the data format of the compression request result obtained by pressure measurement by using different pressure measurement engines can be standardized, and when the pressure measurement system 100 performs data analysis on the target compression request result after format conversion, data format adaptation for each pressure measurement engine is not needed, thereby effectively improving the efficiency of data analysis and reducing the hardware resources of the pressure measurement system 100 occupied by data analysis.

In the embodiment of the present specification, the setting format may be set according to actual conditions, or may be set by a user or the pressure measurement system 100, and the present specification is not particularly limited.

Specifically, the pressure measurement engine used by the pressure measurement system 100 is, for example, an Apache JMeter pressure measurement system, a Grinder pressure measurement system, or the like, and the format of the compression request result obtained by pressure measurement by the Apache JMeter pressure measurement system is different from the format of the compression request result obtained by pressure measurement by the Grinder pressure measurement system, so that the format converter can convert the compression request results obtained by the two pressure measurement systems into the set format.

In addition, since the format converter is disposed in each of the pressure servers in the pressure server cluster 200, and the pressure server cluster 200 does not carry a service system, and naturally supports fast flexible expansion and contraction capacity, the format converter also has the capability, that is, the more pressure servers, the larger the size of the format converter cluster, the stronger the conversion capability, and the workload of data analysis of the pressure measurement system 100 can be effectively reduced, thereby further improving the efficiency of data analysis.

For example, with the transmitting servers in the transmitting server cluster 200 as a1, a2, a3 and a4, and the servers under test in the server cluster under test 300 are b1, b2, b3 and b4 for example, the pressure measurement system 100 receives a creation instruction for creating a pressure measurement task, then creating a pressure measurement task, entering a configuration page of the pressure measurement task, receiving configuration operation of a user on the configuration page, acquiring configuration parameters of the pressure measurement task, the configuration parameters include 100 requests per press test for a1, a2, and a3, 200 requests per second for a4, and the pressure time duration of a, a2, a3 and a4 are all 1 minute, and the corresponding relation between each pressure sending server and the tested server is determined, the correspondence relationship is specifically that a1 corresponds to b1, a2 corresponds to b2, a3 corresponds to b3, and a4 corresponds to b 4.

After acquiring the configuration parameters and the corresponding relations, the pressure measurement system 100 sends the configuration parameters and the corresponding relations to a1, a2, a3 and a4, so that the a1 determines the pressure sending parameters of a1 according to the configuration parameters and the corresponding relations, the pressure sending parameters generate 100 pressure measurement requests per second and last for 1 minute, and then the a1 sends pressure to b1 according to the pressure sending parameters, namely sends 100 pressure measurement requests to b1 per second and then lasts for 1 minute; accordingly, according to the configuration parameters, a2 sends 100 pressure measurement requests to b2 every second and then lasts for 1 minute, a3 sends 100 pressure measurement requests to b3 every second and then lasts for 1 minute, and a4 sends 100 pressure measurement requests to b4 every second and then lasts for 1 minute.

Further, b1 responds after receiving the pressure measurement request sent by a1 each time, and then obtains a corresponding request result, where the request result includes request time, request time consumption and request data of the pressure measurement request, at this time, b1 receives 100 pressure measurement requests within each second and lasts for 1 minute, b1 responds to each received pressure measurement request, and returns each request result obtained by responding to a1, that is, the total number of pressure measurement requests responded is 100 times × 60 seconds (1 minute) ═ 6000 request results are returned to a 1; correspondingly, b2 responds to the received pressure measurement request sent by a2 each time, and returns each request result obtained by the response to a2, that is, the total number of pressure measurement requests responded is 100 times × 60 seconds (1 minute) and 6000 request results are returned to a 2; b3 responds to 6000 pressure measurement requests sent by a3 and returns generated 6000 request results to a 3; and b4 responds to 12000 pressure measurement requests sent by a4 and returns the generated 12000 request results to a 4.

And a1 takes the pressure measurement request sent for the first time as the starting time, a1 compresses all requests returned by b1 every 1s to obtain a compression request result of a1 until b1 returns a request result corresponding to the pressure measurement request sent by a1, if a1 sends the pressure measurement request to b1 for the first time in 20190807 days 16:20:15s, sends 100 pressure measurement requests to b1 in 2019080716:20:15s, and also sends 100 pressure measurement requests to b1 every second in the following 59s, a1 receives 50 request results sent by b1 in 2019080716:20:15s, wherein the request of 40 request results in 50 request results takes 1 ms, the request of 5 request results takes 2 ms, and the request of 5 request results takes 4 ms; then compressing 50 request results to obtain the first compression request result of 2019080716:20:15, 50(50 pressure measurement requests), 50 (the total time of the requests is 1 × 40+2 × 5+4 × 5 ═ 70 milliseconds); and receiving 120 request results sent by b1 at 2019080716:20:16s, wherein the time consumption of 50 request results in the 120 request results is 2 milliseconds, the time consumption of 50 request results is 4 milliseconds, and the time consumption of 20 request results is 5 milliseconds; then compressing the 120 request results to obtain a second compression request result of 2019080716:20:16, 120,400 (400 ms for 50 × 2+50 × 4+20 × 5); the above operations are then performed in sequence until such time as a1 receives b1 returning 6000 request results. For example, the time for b1 to return the request result last is 2019080716:21:20s, the above operation is performed for every second from 2019080716:20:15s to 2019080716:21:20s, so as to obtain the compression request result every second, and the compression request result obtained every second is returned to the pressure measurement system 100.

The operations are executed for a1, a2, a3 and a4, each pressure server acquires the corresponding compression request results every 1s, all the acquired compression request results are returned to the pressure measurement system 100, and after receiving all the compression request results, the pressure measurement system 100 analyzes all the compression request results and then performs data analysis to obtain the pressure measurement report.

Thus, each of the servers compresses all the request results obtained every 1s (set duration) to obtain one compressed request result, so that only one compressed request result needs to be uploaded to the pressure measurement system 100 within 1s, whereas multiple pressure measurement requests such as 50 or 60 times generally exist within 1s and only one compressed request result needs to be uploaded, that is, multiple pressure measurement requests exist within 1s and only one pressure measurement request result needs to be uploaded, whereas in the prior art, the request result corresponding to each obtained pressure measurement request needs to be uploaded once, whereas in the technical solution of the present specification, when multiple pressure measurement requests exist within 1s and only one compressed request result needs to be uploaded once, so that the number of times of uploading of each server every 1s is reduced, and when the compressed request result is formed by compressing multiple request results, compared with the result of multiple requests uploaded, the data volume uploaded by the method is reduced, the data volume uploaded can be effectively reduced, and the uploading frequency is reduced.

In this embodiment of the present specification, after the pressure measurement system 100 receives the compression request result sent by each pressure sending server, the pressure measurement system 100 performs data analysis on all the received compression request results by using an hdrHistogram algorithm to obtain an analysis result; and obtaining the pressure measurement report according to the analysis result.

Specifically, after the pressure measurement system 100 receives the compression request results sent by each pressure sending server, the pressure measurement system 100 analyzes all the received compression request results to obtain all the request results, and performs data analysis on all the request results analyzed by the pressure measurement system 100 based on the hdrHistopram algorithm to obtain the analysis results; and obtaining the pressure measurement report according to the analysis result.

Specifically, the analysis result may include a set quantile of response time of each successful request, wherein the set quantile may be between 1 and 100, and the response time of each successful request may be represented by RT (responsiveness). When the set quantiles are 50, 90 and 99, the analysis result comprises 50RT, 90RT and 99RT, wherein 50RT is 50 quantiles of response time of each successful request, 90RT is 90 quantiles of response time of each successful request, and 99RT is 99 quantiles of response time of each successful request; similarly, when the set value is 50, the analysis result includes 50 RT; and when the set value is 90, the analysis result comprises 90 RT; and when the set value is 99, the analysis result comprises 99 RT; and when the set values are 50 and 90, the analysis result includes 50RT and 90RT, and the present specification is not particularly limited.

In the examples of the present specification, 50/90/99 quantile: sorting the numbers in the sample set from small to large, and then taking out the value of the fifty percent position in the new set, namely the 50 quantile; similarly, the value ranked ninety-th percent is a 90 quantile; similarly, the value ranked ninety nine percent is the 99 quantile, and so on.

Specifically, the pressure measurement system 100 may analyze all the compression request results to obtain all the request results, and then may convert the request time consumption in all the request results obtained through analysis into a preset format, where the preset format includes an actual value of the request time consumption and an occurrence frequency. Specifically, the time consumed by the request in all the request results obtained by the parsing may be converted into K: and V format, wherein K represents the time consumption of the request, and V represents the number of times the time consumption of the request occurs. Of course, if the time consumed by the request in each of the compression request results has been compressed to K: v format, then V can be directly counted to K in each compressed request result, and further the request time consumption in all the request results can be converted into K: v format, and the specification is not particularly limited.

Of course, when converting the request time consumption in all the request results into the K: V format, for each compressed request result, if the compressed request result is formed by compressing N request results, the compressed request result includes the request time consumption of each request result in the N request results.

Specifically, when the percentile is calculated by the HdrHistogram, the percentile can be quickly calculated according to the occurrence value and the occurrence frequency, and the following specific implementation steps are taken as follows, taking 50RT as an example:

step S1, assuming that the behavior K1: V1| K2: V2| K3: V3 needs to be calculated, where K1< K2< K3a 2);

after step S2 and HdrHistogram algorithm addition (K1, V1), 50RT ═ K1;

after step S3 and the HdrHistogram algorithm is added (K2, V2), if V2/(V1+ V2) >0.5, then 50RT is K2; otherwise, 50RT ═ K1;

after step S4 and the HdrHistogram algorithm is added (K3, V3), if V3/(V1+ V2+ V3) >0.5, 50RT is K3; otherwise, 50RT is unchanged, i.e. the value calculated in step S3;

for example, if in step S3 the value 50RT is K2, where V3/(V1+ V2+ V3) ≦ 0.5, then the value 50RT is K2; if the 50RT is K1 in step S3, in this case, V3/(V1+ V2+ V3) ≦ 0.5, the 50RT is K1.

Accordingly, when calculating 90RT, the value 0.5 in steps S3 and S4 may be changed to 0.9, specifically, in step S3, after the HdrHistogram algorithm is added (K2, V2), if V2/(V1+ V2) >0.9, 50RT ═ K2; otherwise, 50RT ═ K1; and, in step S4, after the HdrHistogram algorithm adds (K3, V3), if V3/(V1+ V2+ V3) >0.9, then 50RT ═ K3; otherwise, 50RT is not changed, i.e., is the value calculated in step S3.

Similarly, 99RT can be calculated according to the method, so that a flow type calculation cluster is used for writing calculation results obtained by calculation of the HdrHistogram algorithm into a cache for storage in real time, and meanwhile, a timing task can persist the results in the cache into a corresponding database; and the pressure measurement report can pull the calculation result from the cache for displaying, so that a user can check pressure measurement data in real time.

Thus, the AVLTreeDigest algorithm is employed to calculate the 50, 90 or 99 score RT relative to the prior art, whereas the AVLTreeDigest algorithm is implemented as: each time a request result is added into the sample pool, the balanced binary tree can be automatically rotated once to ensure the integral order, so that the calculation times are the same as the total times of the request results; the request time consumption for calculating the percentile by using the hdrHistogram in the embodiment of the present specification can be calculated according to the occurrence value and the occurrence frequency, and the more the occurrence frequency of the request time consumption with the same occurrence value is, the smaller the calculation frequency is, so that the calculation frequency for calculating the percentile can be effectively reduced, and when the calculation is performed according to the occurrence value and the occurrence frequency of the request time consumption, the calculation is performed according to the occurrence frequency when the request time consumption with the same occurrence value is calculated, so that the calculation amount can be effectively reduced; under the condition that the calculation amount is reduced and the calculation times are also reduced, the calculation efficiency can be effectively improved.

In a second aspect, based on the same inventive concept as that of the first aspect, an embodiment of the present specification provides a pressure measurement method, applied in a pressure-sending server cluster, as shown in fig. 2, including:

step S202, receiving configuration parameters sent by a pressure measurement system, wherein the configuration parameters are parameters for configuring a pressure measurement task;

step S204, determining the pressure sending parameters of each pressure sending server in the pressure sending server cluster according to the configuration parameters;

step S206, each pressure sending server sends a pressure measurement request to a corresponding server to be measured in the server cluster to be measured according to the pressure sending parameters of the server to be measured;

and S208, each pressure server receives a request result returned by the corresponding tested server, wherein for each pressure server, the pressure server compresses all the received request results every set time length to obtain a compression request result of the pressure server, and the pressure server sends the compression request result of the pressure server to the pressure testing system, so that the pressure testing system receives the compression request result sent by each pressure server.

In an optional implementation manner, for each pressure server, the pressure server compresses all received request results every set time length to obtain a compressed request result of the pressure server, including:

and for each pressure sending server, compressing all received request results every the set time length according to the analysis indexes of the data analysis model to obtain the compression request results of the pressure sending server, wherein the data analysis model is a model for performing data analysis on the compression request results by the pressure measurement system.

In an optional implementation manner, for each sending server, according to an analysis index of the data analysis model, the sending server compresses all received request results every set time length to obtain a compressed request result of the sending server, including:

and if the analysis indexes comprise request consumption, compressing all received request results by the pressure sending server every other set time according to the analysis indexes and obtaining a compression request result of the pressure sending server, wherein the compression request result comprises an actual value and occurrence times of the request consumption.

In an optional implementation manner, for each of the sending servers, the sending server compresses all received request results every set time length, and after obtaining the compressed request results of the sending server, the method further includes:

and for each pressure server, after the compression request result of the pressure server is obtained, the pressure server performs format conversion on the compression request result of the pressure server to obtain a target compression request result of the pressure server, wherein the data format in the target compression request result conforms to the set format.

In an optional implementation manner, for each of the pressure servers, after obtaining the compression request result of the pressure server, the pressure server performs format conversion on its own compression request result to obtain a target compression request result of the pressure server, including:

and for each transmitting server, after the compression request result of the transmitting server is obtained, the transmitting server performs format conversion on the compression request result of the transmitting server through a format converter to obtain a target compression request result of the transmitting server, wherein the format converter is arranged in the transmitting server.

In a third aspect, based on the same inventive concept as the first aspect, an embodiment of the present specification provides a method for analyzing pressure measurement data, as shown in fig. 3, applied to a pressure measurement system, including:

step S302, obtaining configuration parameters of a pressure measurement task, and sending the configuration parameters to a pressure sending server cluster;

step S304, receiving a compression request result sent by each pressure sending server in the pressure sending server cluster, wherein each compression request result is obtained by compressing all received request results every set time length by the corresponding pressure sending server;

step S306, performing data analysis on all the compression request results received by using an HdrHistopram algorithm to obtain analysis results;

and S308, obtaining the pressure measurement report according to the analysis result.

In an optional implementation manner, the performing, by using the HdrHistogram algorithm, data analysis on the results of receiving all the compression requests to obtain analysis results includes:

analyzing all the received compression request results to obtain all the request results;

and performing data analysis on all the request results obtained by analysis by using an HdrHistopram algorithm to obtain the analysis result, wherein the analysis result comprises a set quantile of response time of each successful request.

In an optional implementation manner, the performing, by using the HdrHistogram algorithm, data analysis on all the request results obtained by the parsing to obtain the analysis result includes:

converting the request consumed time in all the request results obtained by analysis into a preset format, wherein the preset format comprises an actual value and occurrence times of the request consumed time;

and performing data analysis on all the request results converted into the preset format by using an HdrHistopram algorithm to obtain the analysis result.

In a fourth aspect, based on the same inventive concept as the second aspect, embodiments of the present specification provide a pressure device, as shown in fig. 4, including:

a configuration parameter receiving unit 401, configured to receive a configuration parameter sent by a pressure measurement system, where the configuration parameter is a parameter configuring a pressure measurement task;

a voltage sending parameter determining unit 402, configured to determine, according to the configuration parameter, a voltage sending parameter of each voltage sending server in the voltage sending server cluster;

a pressure measurement request sending unit 403, configured to send, by each pressure sending server, a pressure measurement request to a corresponding server to be measured in the server cluster to be measured according to the pressure sending parameter of the pressure sending server;

a request result receiving unit 404, configured to receive, by each pressure sending server, a request result returned by a corresponding server under test;

a request result compressing and sending unit 405, configured to compress, for each pressure server, all received request results every set time duration by the pressure server to obtain a compression request result of the pressure server, and send, by the pressure server, a compression request result of the pressure server to the pressure measurement system, so that the pressure measurement system receives the compression request result sent by each pressure server.

In an optional implementation manner, the request result compressing and sending unit 405 is configured to, for each pressure server, compress all received request results every other set time interval according to an analysis index of a data analysis model to obtain a compression request result of the pressure server, where the data analysis model is a model for performing data analysis on the compression request result by the pressure measurement system.

In an optional implementation manner, the request result compressing and sending unit 405 is configured to, if the analysis index includes request consumption, compress, by using the pressure server, all received request results every other set time according to the analysis index, to obtain a compression request result of the pressure server, where the compression request result includes an actual value of the request consumption time and an occurrence frequency.

In an optional embodiment, the pressure device further comprises:

and the format conversion unit is used for performing format conversion on the compression request result of each pressure server after the compression request result of the pressure server is obtained for each pressure server to obtain a target compression request result of the pressure server, wherein the data format in the target compression request result conforms to the set format.

In an optional embodiment, the format conversion unit is configured to, for each of the sending servers, after obtaining the compression request result of the sending server, format-convert the compression request result of the sending server by a format converter to obtain a target compression request result of the sending server, where the format converter is disposed in the sending server.

In a fifth aspect, based on the same inventive concept as the third aspect, embodiments of the present specification provide an apparatus for analyzing pressure measurement data, as shown in fig. 5, including:

a configuration parameter obtaining and sending unit 501, configured to obtain a configuration parameter of a pressure measurement task, and send the configuration parameter to a pressure sending server cluster;

a compression request result receiving unit 502, configured to receive a compression request result sent by each of the pressure servers in the pressure server cluster, where each of the compression request results is obtained by compressing all received request results every set time length by the corresponding pressure server;

a data analysis unit 503, configured to perform data analysis on the received compression request results by using an HdrHistogram algorithm, so as to obtain analysis results;

a pressure measurement report obtaining unit 504, configured to obtain the pressure measurement report according to the analysis result.

In an optional implementation manner, the data analysis unit 503 is configured to parse all the compression request results received to obtain all the request results; and performing data analysis on all the request results obtained by analysis by using an HdrHistopram algorithm to obtain the analysis result, wherein the analysis result comprises a set quantile of response time of each successful request.

In an optional implementation manner, the data analysis unit 503 is configured to convert the request time consumption in all the obtained request results into a preset format, where the preset format includes an actual value of the request time consumption and an occurrence number; and performing data analysis on all the request results converted into the preset format by using an HdrHistopram algorithm to obtain the analysis result.

In a sixth aspect, based on the same inventive concept as the pressure measurement method and the pressure measurement data analysis method in the foregoing embodiments, an embodiment of the present specification further provides an electronic device, as shown in fig. 6, including a memory 604, a processor 602, and a computer program stored in the memory 604 and executable on the processor 602, where the processor 602, when executing the program, implements the steps of any one of the pressure measurement method and the pressure measurement data analysis method.

Where in fig. 6 a bus architecture (represented by bus 600) is shown, bus 600 may include any number of interconnected buses and bridges, and bus 600 links together various circuits including one or N processors, represented by processor 602, and memory, represented by memory 604. The bus 600 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 605 provides an interface between the bus 600 and the receiver 601 and transmitter 603. The receiver 601 and the transmitter 603 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 602 is responsible for managing the bus 600 and general processing, and the memory 604 may be used for storing data used by the processor 602 in performing operations.

In a seventh aspect, based on the inventive concept similar to the pressure measurement method and the pressure measurement data analysis method in the foregoing embodiments, the present specification further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any one of the pressure measurement method or the pressure measurement data analysis method described above.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a server, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present specification have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all changes and modifications that fall within the scope of the specification.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present specification without departing from the spirit and scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the specification is intended to include such modifications and variations.

Claims

1. A pressure measurement method is applied to a pressure sending server cluster and comprises the following steps:

2. The pressure measurement method according to claim 1, wherein for each pressure server, the pressure server compresses all received request results every set time period to obtain a compressed request result of the pressure server, and the method comprises:

3. The pressure measurement method according to claim 2, wherein for each pressure server, the pressure server compresses all received request results every the set time period according to an analysis index of the data analysis model to obtain a compressed request result of the pressure server, and the method comprises:

4. The pressure measurement method according to any one of claims 1 to 3, wherein for each pressure server, the pressure server compresses all received request results every set time period, and after obtaining the compression request results of the pressure server, the method further comprises:

5. The pressure measurement method according to claim 4, wherein for each of the pressure servers, after obtaining the compression request result of the pressure server, the pressure server performs format conversion on the compression request result thereof to obtain the target compression request result of the pressure server, and the method comprises:

6. A method for analyzing pressure measurement data is applied to a pressure measurement system and comprises the following steps:

and obtaining the pressure measurement report according to the analysis result.

7. The analysis method according to claim 6, wherein the performing data analysis on the received results of all the compression requests by using the hdrHistogram algorithm to obtain an analysis result comprises:

8. The analysis method according to claim 7, wherein the performing data analysis on all the analyzed request results by using the hdrHistory algorithm to obtain the analysis result comprises:

9. A pressure device comprising:

10. The device according to claim 9, wherein the request result compressing and sending unit is configured to, for each voltage sending server, compress all received request results every other set time interval according to an analysis index of a data analysis model to obtain a compression request result of the voltage sending server, where the data analysis model is a model for performing data analysis on the compression request result by the voltage measurement system.

11. The device according to claim 10, wherein the request result compressing and sending unit is configured to, if the analysis indicator includes a request consumption, compress, by using the voltage sending server, all received request results every other set time according to the analysis indicator, to obtain a compression request result of the voltage sending server, where the compression request result includes an actual value of the request consumption time and an occurrence frequency.

12. The voltage device of any of claims 9-11, further comprising:

13. The device according to claim 12, wherein the format conversion unit is configured to, for each voltage sending server, after obtaining the compression request result of the voltage sending server, format-convert the compression request result of the voltage sending server by a format converter to obtain the target compression request result of the voltage sending server, where the format converter is disposed in the voltage sending server.

14. An apparatus for analyzing pressure measurement data, comprising:

15. The analysis device as claimed in claim 14, wherein the data analysis unit is configured to parse all the compression request results received to obtain all the request results; and performing data analysis on all the request results obtained by analysis by using an HdrHistopram algorithm to obtain the analysis result, wherein the analysis result comprises a set quantile of response time of each successful request.

16. The analysis device according to claim 15, wherein the data analysis unit is configured to convert a request consuming time in all the obtained request results into a preset format, where the preset format includes an actual value of the request consuming time and an occurrence number; and performing data analysis on all the request results converted into the preset format by using an HdrHistopram algorithm to obtain the analysis result.

17. A pressure measuring platform comprises a pressure measuring system, a pressure sending server cluster and a measured server cluster, and comprises:

18. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1-8 when executing the program.

19. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.