转:apache自带的压力测试工具 (apache benchmark )


简介
ab的全称是ApacheBench,是 Apache 附带的一个小工具,专门用于 HTTP Server 的benchmark testing,可以同时模拟多个并发请求。前段时间看到公司的开发人员也在用它作一些测试,看起来也不错,很简单,也很容易使用,所以今天花一点时间看了一下。
通过下面的一个简单的例子和注释,相信大家可以更容易理解这个工具的使用。
一个简单的例子
/*在这个例子的一开始,我执行了这样一个命令 ab -n 10 -c 10 http://www.xxxx.xxx/。这个命令的意思是启动 ab ,向 www.xxxx.xxx 发送10个请求(-n 10) ,并每次发送10个请求(-c 10)——也就是说一次都发过去了。跟着下面的是 ab 输出的测试报告,红色部分是我添加的注释。*/
C:\Program Files\Apache Software Foundation\Apache2.2\bin>ab -n 10 -c 10 http
://www.xxxx.xxx/
This is ApacheBench, Version 2.0.40-dev <$Revision: 1.146 $> apache-2.0
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Copyright 1997-2005 The Apache Software Foundation, http://www.apache.org/
Benchmarking www.google.com (be patient).....done
Server Software: GWS/2.1
Server Hostname: www.xxxx.xxx
Server Port: 80
Document Path: /
Document Length: 230 bytes
Concurrency Level: 10
/*整个测试持续的时间*/
Time taken for tests: 3.234651 seconds
/*完成的请求数量*/
Complete requests: 10
/*失败的请求数量*/
Failed requests: 0
Write errors: 0
Non-2xx responses: 10
Keep-Alive requests: 10
/*整个场景中的网络传输量*/
Total transferred: 6020 bytes
/*整个场景中的HTML内容传输量*/
HTML transferred: 2300 bytes
/*大家最关心的指标之一,相当于 LR 中的 每秒事务数 ,后面括号中的 mean 表示这是一个平均值*/
Requests per second: 3.09 [#/sec] (mean)
/*大家最关心的指标之二,相当于 LR 中的 平均事务响应时间 ,后面括号中的 mean 表示这是一个平均值*/
Time per request: 3234.651 [ms] (mean)
/*每个事物的响应时间 */
Time per request: 323.465 [ms] (mean, across all concurrent requests)
/*平均每秒网络上的流量,可以帮助排除是否存在网络流量过大导致响应时间延长的问题*/
Transfer rate: 1.55 [Kbytes/sec] received
/*网络上消耗的时间的分解,各项数据的具体算法还不是很清楚*/
Connection Times (ms)
min mean[+/-sd] median max
Connect: 20 318 926.1 30 2954
Processing: 40 2160 1462.0 3034 3154
Waiting: 40 2160 1462.0 3034 3154
Total: 60 2479 1276.4 3064 3184
/*下面的内容为整个场景中所有请求的响应情况。在场景中每个请求都有一个响应时间,其中 50% 的用户响应时间小于 3064 毫秒,60 % 的用户响应时间小于 3094 毫秒,最大的响应时间小于 3184 毫秒*/
Percentage of the requests served within a certain time (ms)
50% 3064
66% 3094
75% 3124
80% 3154
90% 3184
95% 3184
98% 3184
99% 3184
100% 3184 (longest request)
参数详解
ab is a tool for benchmarking your Apache Hypertext Transfer Protocol(HTTP) server. It is designed to give you an impression of how your current Apache installation performs. This especially shows you how many requests per second your Apache installation is capable of serving.
ab是Apache超文本传输协议(HTTP)的性能测试工具。 其设计意图是描绘当前所安装的Apache的执行性能, 主要是显示你安装的Apache每秒可以处理多少个请求。
OPTIONS
-A auth-username:password
Supply BASIC Authentication credentials to the server. The user name and password are separated by a single : and sent on the wire base64 encoded. The string is sent regardless of whether the server needs it (i.e., has sent an 401 authentication needed).
对服务器提供BASIC认证信任。 用户名和密码由一个:隔开,并以base64编码形式发送。 无论服务器是否需要(即, 是否发送了401认证需求代码),此字符串都会被发送。
-c concurrency
Number of multiple requests to perform at a time. Default is one request at a time.
一次产生的请求个数。默认是一次一个。
-C cookie-name=value
Add a Cookie: line to the request. The argument is typically in the form of a name=value pair. This field is repeatable.
对请求附加一个Cookie:行。 其典型形式是name=value的一个参数对。 此参数可以重复。
-d Do not display the "percentage served within XX [ms] table".
(legacy support).
不显示"percentage served within XX [ms] table"的消息(为以前的版本提供支持)。
-e csv-file
Write a Comma separated value (CSV) file which contains for each percentage (from 1% to 100%) the time (in milliseconds) it took to serve that percentage of the requests. This is usually more useful than the 'gnuplot' file; as the results are already 'binned'.
产生一个以逗号分隔的(CSV)文件, 其中包含了处理每个相应百分比的请求所需要(从1%到100%)的相应百分比的(以毫秒为单位)时间。 由于这种格式已经“二进制化”,所以比'gnuplot'格式更有用。
-g gnuplot-file
Write all measured values out as a 'gnuplot' or TSV (Tab separate values) file. This file can easily be imported into packages like Gnuplot, IDL, Mathematica, Igor or even Excel. The labels are on the first line of the file.
把所有测试结果写入一个'gnuplot'或者TSV (以Tab分隔的)文件。 此文件可以方便地导入到Gnuplot, IDL, Mathematica, Igor甚至Excel中。 其中的第一行为标题。
-h Display usage information.
显示使用方法。
-H custom-header
Append extra headers to the request. The argument is typically in the form of a valid header line, containing a colon-separated field-value pair (i.e., "Accept-Encoding: zip/zop;8bit").
对请求附加额外的头信息。 此参数的典型形式是一个有效的头信息行,其中包含了以冒号分隔的字段和值的对 (如, "Accept-Encoding: zip/zop;8bit").
-i Do HEAD requests instead of GET.
执行HEAD请求,而不是GET。
-k Enable the HTTP KeepAlive feature, i.e., perform multiple
requests within one HTTP session. Default is no KeepAlive.
启用HTTP KeepAlive功能,即, 在一个HTTP会话中执行多个请求。 默认是不启用KeepAlive功能.
-n requests
Number of requests to perform for the benchmarking session. The default is to just perform a single request which usually leads to non-representative enchmarking results.
在测试会话中所执行的请求个数。 默认时,仅执行一个请求,但通常其结果不具有代表意义。
-p POST-file
File containing data to POST.
包含了需要POST的数据的文件.
-P proxy-auth-username:password
Supply BASIC Authentication credentials to a proxy en-route. The username and password are separated by a single : and sent on the wire base64 encoded. The string is sent regardless of whether the proxy needs it (i.e., has sent an 407 proxy authentication needed).
对一个中转代理提供BASIC认证信任。 用户名和密码由一个:隔开,并以base64编码形式发送。 无论服务器是否需要(即, 是否发送了401认证需求代码),此字符串都会被发送。
-q When processing more than 150 requests, ab outputs a progress count on stderr every 10% or 100 requests or so. The -q flag will suppress these messages.
如果处理的请求数大于150, ab每处理大约10%或者100个请求时,会在stderr输出一个进度计数。 此-q标记可以抑制这些信息。
-s When compiled in (ab -h will show you) use the SSL protected https rather than the http protocol. This feature is experimental and very rudimentary. You probably do not want to use it.
用于编译中(ab -h会显示相关信息)使用了SSL的受保护的https, 而不是http协议的时候。此功能是实验性的,也是很简陋的。最好不要用。
-S Do not display the median and standard deviation values, nor display the warning/error messages when the average and median are more than one or two times the standard deviation apart. And default to the min/avg/max values. (legacy support).
不显示中值和标准背离值, 而且在均值和中值为标准背离值的1到2倍时,也不显示警告或出错信息。 默认时,会显示 最小值/均值/最大值等数值。(为以前的版本提供支持).
-t timelimit
Maximum number of seconds to spend for benchmarking. This implies a -n 50000 internally. Use this to benchmark the server within a fixed total amount of time. Per default there is no timelimit.
测试所进行的最大秒数。其内部隐含值是-n 50000。 它可以使对服务器的测试限制在一个固定的总时间以内。默认时,没有时间限制。
-T content-type
Content-type header to use for POST data.
POST数据所使用的Content-type头信息。
-v verbosity
Set verbosity level - 4 and above prints information on headers, 3 and above prints response codes (404, 200, etc.), 2 and above prints warnings and info.
设置显示信息的详细程度 - 4或更大值会显示头信息, 3或更大值可以显示响应代码(404, 200等), 2或更大值可以显示警告和其他信息。
-V Display version number and exit.
显示版本号并退出。
-w Print out results in HTML tables. Default table is two columns wide, with a white background.
以HTML表的格式输出结果。默认时,它是白色背景的两列宽度的一张表。
-x

-attributes
String to use as attributes for

. Attributes are inserted

.
设置

属性的字符串。 此属性被填入.
-X proxy[:port]
Use a proxy server for the requests.
对请求使用代理服务器。
-y

-attributes
String to use as attributes for

.
设置

属性的字符串.
-z

-attributes
String to use as attributes for

.
设置

属性的字符串.
BUGS
There are various statically declared buffers of fixed length. Combined with the lazy parsing of the command line arguments, the response headers from the server and other external inputs, this might bite you. It does not implement HTTP/1.x fully; only accepts some 'expected' forms of responses. The rather heavy use of strstr(3) shows up top in profile, which might indicate a performance problem; i.e., you would measure the ab performance rather than the server's.
程序中有各种静态声明的固定长度的缓冲区。另外,对命令行参数、服务器的响应头和其他外部输入的解析也很简单,这可能会有不良后果。它没有完整地实现HTTP/1.x; 仅接受某些'预想'的响应格式。strstr(3)的频繁使用可能会带来性能问题,即, 你可能是在测试ab而不是服务器的性能。

via:http://5iwww.blog.51cto.com/856039/226457

Archives