Apache AB Test

Analysis of Apache AB performance test results

Transferred from: https://www.cnblogs.com/gumuzi/p/5617232.html

I've been using LoadRunner to do performance testing all the time. LoadRunner is actually a very heavy performance testing tool. His function is very comprehensive, is a very good sledgehammer.

If we just need to do a simple performance test on a page, using Loadruner This sledgehammer is not a good choice.

So I found a knife--ab to try. This knife is really light and sharp, here is a record of the AB test process of some of their own understanding, for your reference.

We will take Baidu homepage to sacrifice knife bar. First you have to have a knife, that is, the installation of Apache, a lot of online tutorials are no longer described, this article uses the MacBook's own AB command to test.

　　test Scenario : Simulate 10 users, the Baidu home page launched a total of 100 requests.

　　Test Command : ab-n 100-c https://www.baidu.com/index.html

This article mainly for AB test report analysis, the use of AB on another day to open a new exchange.

　　Test Report :

　　

Below to explain my understanding on a line, the following comments are read on the online materials, but the content is written for their own understanding after the content, hoping to join their own understanding can make the reader easier to understand.

bogon:~ tang$ ab-n 100-c https://www.baidu.com/index.html

This is apachebench, Version 2.3 < $Revision: 1706008 $>

Copyright 1996 Adam Twiss, Zeus technology LTD, http://www.zeustech.net/

Licensed to the Apache software Foundation, http://www.apache.org/

The above is the Apache version information, not related to this test

Benchmarking www.baidu.com (Be patient) ... done

The above content displays the test completion degree, this test initiates the request quantity to be small, completes faster, does not have the intermediate process display. When the number of requests is large, the current number of finishes is displayed on a branch.

Server software:bfe/1.0.8.14//tested servers used by the software information, the use of Baidu's own development of the reverse proxy Baidu Front End, similar to Nginx.

Server Hostname:www.baidu.com//host name under test

Server port:443//The service port number of the host being tested, the default port number of the general HTTP request is 80,HTTPS 443 port is used by default

SSL/TLS PROTOCOL:TLSV1.2,ECDHE-RSA-AES128-GCM-SHA256,2048,128//encryption protocol

Document Path:/index.html//Requested specific file

Document length:227 Bytes//requested file index.html size

Concurrency level:10//concurrency level, which is the number of concurrent numbers specified by the-c parameter in the request

Time taken for tests:1.093 seconds//This test takes a total of

Total requests:100//number of requests initiated in this test

Failed requests:0//number of failed requests. Due to network or server performance reasons, the originating request is not necessarily all successful, by dividing this number and complete requests to calculate the failure rate of the request as an important reference for the test results.

Total transferred:103314 Bytes//The amount of data transmitted in total refers to the amount of data ab receives from the server under test, including index.html text content and request header information.

HTML transferred:22700 Bytes//The total size of the index.html file received from the server equals document Length*complete requests=227 bytes*100=22700 byt Es

Requests per second:91.50 [#/sec] (mean)//average (mean) number of requests completed per second: QPS, which is an average, equals complete requests/time taken for TESTS=100/1 .093=91.50

Time per request:109.287 [MS] (mean)//from the user's point of view, to complete a request (due to the number of users more than one, the server completes 10 requests, the average user receives a full return, so this value is 10 times times the next value.) ）

Time per request:10.929 [MS] (mean, across all concurrent requests)//server completes a request.

Transfer rate:92.32 [Kbytes/sec] Received//network transfer speed. For large file request testing, this value can easily become a system bottleneck. To determine if the value is a bottleneck, you need to understand the network situation between the client and the server under test, including information such as network bandwidth and Nic speed.

Connection Times (MS)

Min MEAN[+/-SD] Median max

CONNECT:47 74 12.9 74 106

Processing:9 32 20.2 32 106

Waiting:9 29 19.1 27 98

TOTAL:66 106 20.8 106 195

The tables made up of these lines are subdivided and counted mainly for response times, the first time per request. The response time of a request can be divided into network link (Connect), System processing (processing) and wait (waiting) three parts. The min in the table represents the minimum value, the mean means the mean, [+/-SD] represents the standard deviation, or the mean variance (mean square error), which is taught in the math class in high school, which indicates the degree of dispersion of the data. The larger the value, the more fragmented the data, and the more unstable the system response time. Median represents the median; Max is of course the maximum value.

It is important to note that total in the table is not equal to the first three rows of data, because the first three rows of data are not collected in the same request, perhaps the network latency of a request is the shortest, but the system processing time is the longest. So total is counted from the point of view of the time required for the entire request. Here you can see that the slowest request cost 195ms, and this data can be verified in the table below.

Percentage of the requests served within a certain time (MS)

50% 106

66% 109

75% 111

80% 114

90% 118

95% 154

98% 176

99% 195

100% 195 (Longest request)

The first line of this table indicates that 50% of the requests are completed in 106ms, and you can see that this value is closer to the average system response time (the first one is request:109.287 [MS] (mean))

And so on, 90% of the requests are less than or equal to 118ms. Just now we see that the longest response time is 195ms, so it is clear that all requests (100%) are less than or equal to 195 milliseconds, and that is, the last row in the table must be the longest one (longest request).

I believe we can understand the meaning of this data through the above instructions. Please leave a message if you have any errors.

Apache AB Test