rolling-curl完整版下载地址
https://github.com/LionsAd/rolling-curl
curl_multi在抓取数据中的并发实现(查看curl_multi函数的详细介绍)
cURL multi批处理实现及避免cURL multi造成CPU负载过高问题
php中curl_multi的应用 同时请求多个url
<?php
/*
authored by Josh Fraser (www.joshfraser.com)
released under Apache License 2.0
Maintained by Alexander Makarov, http://rmcreative.ru/
$Id$
*/
// a little example that fetches a bunch of sites in parallel and echos the page title and response info for each request
function request_callback($response, $info) {
// parse the page title out of the returned HTML
if (preg_match("~<title>(.*?)</title>~i", $response, $out)) {
$title = $out[1];
}
echo "<b>$title</b><br />";
print_r($info);
echo "<hr>";
}
require("RollingCurl.php");
// single curl request
$rc = new RollingCurl("request_callback");
$rc->request("http://www.msn.com");
$rc->execute();
// another single curl request
$rc = new RollingCurl("request_callback");
//request 方法 参数是网址
$rc->request("http://www.google.com");
$rc->request("http://www.baidu.com");
$rc->execute();
echo "<hr>";
// top 20 sites according to alexa (11/5/09)
$urls = array("http://www.google.com",
"http://www.facebook.com",
"http://www.yahoo.com",
"http://www.youtube.com",
"http://www.live.com",
"http://www.wikipedia.com",
"http://www.blogger.com",
"http://www.msn.com",
"http://www.baidu.com",
"http://www.yahoo.co.jp",
"http://www.myspace.com",
"http://www.qq.com",
"http://www.google.co.in",
"http://www.twitter.com",
"http://www.google.de",
"http://www.microsoft.com",
"http://www.google.cn",
"http://www.sina.com.cn",
"http://www.wordpress.com",
"http://www.google.co.uk");
$rc = new RollingCurl("request_callback");
$rc->window_size = 20;
foreach ($urls as $url) {
$request = new RollingCurlRequest($url);
//add 方法 参数是 RollingCurlRequest
$rc->add($request);
}
$rc->execute();
//Example 1 - Hello world:
// an array of URL's to fetch
$urls = array("http://www.google.com",
"http://www.facebook.com",
"http://www.yahoo.com");
// a function that will process the returned responses
function request_callback($response, $info) {
// parse the page title out of the returned HTML
if (preg_match("~<title>(.*?)</title>~i", $response, $out)) {
$title = $out[1];
}
echo "<b>$title</b><br />";
print_r($info);
echo "<hr>";
}
// create a new RollingCurl object and pass it the name of your custom callback function
$rc = new RollingCurl("request_callback");
// the window size determines how many simultaneous requests to allow.
//创建一个新的RollingCurl对象并将其传递给您的自定义回调函数的名称
$rc->window_size = 20;
foreach ($urls as $url) {
// add each request to the RollingCurl object
$request = new RollingCurlRequest($url); //?? RollingCurlRequest
$rc->add($request);
}
$rc->execute();
//Example 2 - Setting custom options:
//Set custom options for EVERY request: 设置自定义选项为每个请求
$rc = new RollingCurl("request_callback");
$rc->options = array(CURLOPT_HEADER => true, CURLOPT_NOBODY => true);
$rc->execute();
//Set custom options for A SINGLE request: 设置自定义选项为单个请求
$rc = new RollingCurl("request_callback");
$request = new RollingCurlRequest($url); // ?? RollingCurlRequest
$request->options = array(CURLOPT_HEADER => true, CURLOPT_NOBODY => true);
$rc->add($request);
$rc->execute();
//Example 3 - Shortcuts: get方法
$rc = new RollingCurl("request_callback");
// 方法类似request 只是指定get方法了
$rc->get("http://www.google.com");
$rc->get("http://www.yahoo.com");
$rc->execute();
//Example 4 - Class callbacks:
class MyInfoCollector {
private $rc;
function __construct(){
$this->rc = new RollingCurl(array($this, 'processPage'));
}
function processPage($response, $info){
//...
}
function run($urls){
foreach ($urls as $url){
$request = new RollingCurlRequest($url);
$this->rc->add($request);
}
$this->rc->execute();
}
}
$collector = new MyInfoCollector();
$collector->run(array(
'http://google.com/',
'http://yahoo.com/'
));
<?php
/*
authored by Josh Fraser (www.joshfraser.com)
released under Apache License 2.0
Maintained by Alexander Makarov, http://rmcreative.ru/
$Id$
*/
// a little example that fetches a bunch of sites in parallel and echos the page title and response info for each request
function request_callback($response, $info) {
// parse the page title out of the returned HTML
if (preg_match("~<title>(.*?)</title>~i", $response, $out)) {
$title = $out[1];
}
echo "<b>$title</b><br />";
print_r($info);
echo "<hr>";
}
require("RollingCurl.php");
// single curl request
$rc = new RollingCurl("request_callback");
$rc->request("http://www.msn.com");
$rc->execute();
// another single curl request
$rc = new RollingCurl("request_callback");
//request 方法 参数是网址
$rc->request("http://www.google.com");
$rc->request("http://www.baidu.com");
$rc->execute();
echo "<hr>";
// top 20 sites according to alexa (11/5/09)
$urls = array("http://www.google.com",
"http://www.facebook.com",
"http://www.yahoo.com",
"http://www.youtube.com",
"http://www.live.com",
"http://www.wikipedia.com",
"http://www.blogger.com",
"http://www.msn.com",
"http://www.baidu.com",
"http://www.yahoo.co.jp",
"http://www.myspace.com",
"http://www.qq.com",
"http://www.google.co.in",
"http://www.twitter.com",
"http://www.google.de",
"http://www.microsoft.com",
"http://www.google.cn",
"http://www.sina.com.cn",
"http://www.wordpress.com",
"http://www.google.co.uk");
$rc = new RollingCurl("request_callback");
$rc->window_size = 20;
foreach ($urls as $url) {
$request = new RollingCurlRequest($url);
//add 方法 参数是 RollingCurlRequest
$rc->add($request);
}
$rc->execute();
//Example 1 - Hello world:
// an array of URL's to fetch
$urls = array("http://www.google.com",
"http://www.facebook.com",
"http://www.yahoo.com");
// a function that will process the returned responses
function request_callback($response, $info) {
// parse the page title out of the returned HTML
if (preg_match("~<title>(.*?)</title>~i", $response, $out)) {
$title = $out[1];
}
echo "<b>$title</b><br />";
print_r($info);
echo "<hr>";
}
// create a new RollingCurl object and pass it the name of your custom callback function
$rc = new RollingCurl("request_callback");
// the window size determines how many simultaneous requests to allow.
//创建一个新的RollingCurl对象并将其传递给您的自定义回调函数的名称
$rc->window_size = 20;
foreach ($urls as $url) {
// add each request to the RollingCurl object
$request = new RollingCurlRequest($url); //?? RollingCurlRequest
$rc->add($request);
}
$rc->execute();
//Example 2 - Setting custom options:
//Set custom options for EVERY request: 设置自定义选项为每个请求
$rc = new RollingCurl("request_callback");
$rc->options = array(CURLOPT_HEADER => true, CURLOPT_NOBODY => true);
$rc->execute();
//Set custom options for A SINGLE request: 设置自定义选项为单个请求
$rc = new RollingCurl("request_callback");
$request = new RollingCurlRequest($url); // ?? RollingCurlRequest
$request->options = array(CURLOPT_HEADER => true, CURLOPT_NOBODY => true);
$rc->add($request);
$rc->execute();
//Example 3 - Shortcuts: get方法
$rc = new RollingCurl("request_callback");
// 方法类似request 只是指定get方法了
$rc->get("http://www.google.com");
$rc->get("http://www.yahoo.com");
$rc->execute();
//Example 4 - Class callbacks:
class MyInfoCollector {
private $rc;
function __construct(){
$this->rc = new RollingCurl(array($this, 'processPage'));
}
function processPage($response, $info){
//...
}
function run($urls){
foreach ($urls as $url){
$request = new RollingCurlRequest($url);
$this->rc->add($request);
}
$this->rc->execute();
}
}
$collector = new MyInfoCollector();
$collector->run(array(
'http://google.com/',
'http://yahoo.com/'
));
<?php
/*
Authored by Josh Fraser (www.joshfraser.com)
Released under Apache License 2.0
Maintained by Alexander Makarov, http://rmcreative.ru/
$Id$
*/
/**
* Class that represent a single curl request
*/
class RollingCurlRequest {
public $url = false;
public $method = 'GET';
public $post_data = null;
public $headers = null;
public $options = null;
/**
* @param string $url
* @param string $method
* @param $post_data
* @param $headers
* @param $options
* @return void
*/
function __construct($url, $method = "GET", $post_data = null, $headers = null, $options = null) {
$this->url = $url;
$this->method = $method;
$this->post_data = $post_data;
$this->headers = $headers;
$this->options = $options;
}
/**
* @return void
*/
public function __destruct() {
unset($this->url, $this->method, $this->post_data, $this->headers, $this->options);
}
}
/**
* RollingCurl custom exception
*/
class RollingCurlException extends Exception {}
/**
* Class that holds a rolling queue of curl requests.
*
* @throws RollingCurlException
*/
class RollingCurl {
/**
* @var int
*
* Window size is the max number of simultaneous connections allowed.
*
* REMEMBER TO RESPECT THE SERVERS:
* Sending too many requests at one time can easily be perceived
* as a DOS attack. Increase this window_size if you are making requests
* to multiple servers or have permission from the receving server admins.
*/
private $window_size = 5;
/**
* @var float
*
* Timeout is the timeout used for curl_multi_select.
*/
private $timeout = 10;
/**
* @var string|array
*
* Callback function to be applied to each result.
*/
private $callback;
/**
* @var array
*
* Set your base options that you want to be used with EVERY request.
*/
protected $options = array(
CURLOPT_SSL_VERIFYPEER => 0,
CURLOPT_RETURNTRANSFER => 1,
CURLOPT_CONNECTTIMEOUT => 30,
CURLOPT_TIMEOUT => 30
);
/**
* @var array
*/
private $headers = array();
/**
* @var Request[]
*
* The request queue
*/
private $requests = array();
/**
* @var RequestMap[]
*
* Maps handles to request indexes
*/
private $requestMap = array();
/**
* @param $callback
* Callback function to be applied to each result.
*
* Can be specified as 'my_callback_function'
* or array($object, 'my_callback_method').
*
* Function should take three parameters: $response, $info, $request.
* $response is response body, $info is additional curl info.
* $request is the original request
*
* @return void
*/
function __construct($callback = null) {
$this->callback = $callback;
}
/** 返回 属性
* @param string $name
* @return mixed
*/
public function __get($name) {
return (isset($this->{$name})) ? $this->{$name} : null;
}
/** 可以设置headers 和 options
* @param string $name
* @param mixed $value
* @return bool
*/
public function __set($name, $value){
// append the base options & headers
if ($name == "options" || $name == "headers") {
$this->{$name} = $value + $this->{$name};
} else {
$this->{$name} = $value;
}
return true;
}
/**
* Add a request to the request queue
*
* @param Request $request
* @return bool
*/
public function add($request) {
$this->requests[] = $request;
return true;
}
/**
* Create new Request and add it to the request queue
*
* @param string $url
* @param string $method
* @param $post_data
* @param $headers
* @param $options
* @return bool
*/
public function request($url, $method = "GET", $post_data = null, $headers = null, $options = null) {
$this->requests[] = new RollingCurlRequest($url, $method, $post_data, $headers, $options);
return true;
}
/**
* Perform GET request
*
* @param string $url
* @param $headers
* @param $options
* @return bool
*/
public function get($url, $headers = null, $options = null) {
return $this->request($url, "GET", null, $headers, $options);
}
/**
* Perform POST request
*
* @param string $url
* @param $post_data
* @param $headers
* @param $options
* @return bool
*/
public function post($url, $post_data = null, $headers = null, $options = null) {
return $this->request($url, "POST", $post_data, $headers, $options);
}
/**
* Execute the curl
*
* @param int $window_size Max number of simultaneous connections
* @return string|bool
*/
public function execute($window_size = null) {
// rolling curl window must always be greater than 1
if (sizeof($this->requests) == 1) {
return $this->single_curl();
} else {
// start the rolling curl. window_size is the max number of simultaneous connections
return $this->rolling_curl($window_size);
}
}
/**
* Performs a single curl request
*
* @access private
* @return string
*/
private function single_curl() {
$ch = curl_init();
$request = array_shift($this->requests);
$options = $this->get_options($request);
curl_setopt_array($ch,$options);
$output = curl_exec($ch);
$info = curl_getinfo($ch);
// it's not neccesary to set a callback for one-off requests
if ($this->callback) {
$callback = $this->callback;
if (is_callable($this->callback)){
call_user_func($callback, $output, $info, $request);
}
}
else
return $output;
return true;
}
/**
* Performs multiple curl requests
*
* @access private
* @throws RollingCurlException
* @param int $window_size Max number of simultaneous connections
* @return bool
*/
private function rolling_curl($window_size = null) {
if ($window_size)
$this->window_size = $window_size;
// make sure the rolling window isn't greater than the # of urls
if (sizeof($this->requests) < $this->window_size)
$this->window_size = sizeof($this->requests);
if ($this->window_size < 2) {
throw new RollingCurlException("Window size must be greater than 1");
}
$master = curl_multi_init();
// start the first batch of requests
for ($i = 0; $i < $this->window_size; $i++) {
$ch = curl_init();
$options = $this->get_options($this->requests[$i]);
curl_setopt_array($ch,$options);
curl_multi_add_handle($master, $ch);
// Add to our request Maps
$key = (string) $ch;
$this->requestMap[$key] = $i;
}
do {
while(($execrun = curl_multi_exec($master, $running)) == CURLM_CALL_MULTI_PERFORM);
if($execrun != CURLM_OK)
break;
// a request was just completed -- find out which one
while($done = curl_multi_info_read($master)) {
// get the info and content returned on the request
$info = curl_getinfo($done['handle']);
$output = curl_multi_getcontent($done['handle']);
// send the return values to the callback function.
$callback = $this->callback;
if (is_callable($callback)){
$key = (string)$done['handle'];
$request = $this->requests[$this->requestMap[$key]];
unset($this->requestMap[$key]);
call_user_func($callback, $output, $info, $request);
}
// start a new request (it's important to do this before removing the old one)
if ($i < sizeof($this->requests) && isset($this->requests[$i]) && $i < count($this->requests)) {
$ch = curl_init();
$options = $this->get_options($this->requests[$i]);
curl_setopt_array($ch,$options);
curl_multi_add_handle($master, $ch);
// Add to our request Maps
$key = (string) $ch;
$this->requestMap[$key] = $i;
$i++;
}
// remove the curl handle that just completed
curl_multi_remove_handle($master, $done['handle']);
}
// Block for data in / output; error handling is done by curl_multi_exec
if ($running)
curl_multi_select($master, $this->timeout);
} while ($running);
curl_multi_close($master);
return true;
}
/**
* Helper function to set up a new request by setting the appropriate options
*
* @access private
* @param Request $request
* @return array
*/
private function get_options($request) {
// options for this entire curl object
$options = $this->__get('options');
if (ini_get('safe_mode') == 'Off' || !ini_get('safe_mode')) {
/*
要使用CURL中的CURLOPT_FOLLOWLOCATION(允许被抓取的链接跳转)
必须关闭安全模式 以及关闭open_basedir
这样的话就会影响服务器的安全性
我也遇到过
301 302跳转后采集的问题
解决办法是合租换 vps
自己配置环
*/
$options[CURLOPT_FOLLOWLOCATION] = 1; //允许被抓取的链接跳转
$options[CURLOPT_MAXREDIRS] = 5; //可以限定递归返回的数量
}
$headers = $this->__get('headers');
// append custom options for this specific request
if ($request->options) {
$options = $request->options + $options;
}
// set the request URL
$options[CURLOPT_URL] = $request->url;
// posting data w/ this request?
if ($request->post_data) {
$options[CURLOPT_POST] = 1;
$options[CURLOPT_POSTFIELDS] = $request->post_data;
}
if ($headers) {
$options[CURLOPT_HEADER] = 0;
$options[CURLOPT_HTTPHEADER] = $headers;
}
return $options;
}
/**
* @return void
*/
public function __destruct() {
unset($this->window_size, $this->callback, $this->options, $this->headers, $this->requests);
}
}
在实际项目或者自己编写小工具(比如新闻聚合,商品价格监控,比价)的过程中, 通常需要从第3方网站或者API接口获取数据, 在需要处理1个URL队列时, 为了提高性能, 可以采用cURL提供的curl_multi_*族函数实现简单的并发.
本文将探讨两种具体的实现方法, 并对不同的方法做简单的性能对比.
curl_multi_select
(PHP 5)
curl_multi_select — 等待所有cURL批处理中的活动连接
说明 ¶
int curl_multi_select ( resource $mh [, float $timeout = 1.0 ] )
阻塞直到cURL批处理连接中有活动连接。
参数 ¶
mh
由 curl_multi_init() 返回的 cURL 多个句柄。
timeout
以秒为单位,等待响应的时间。
返回值 ¶
成功时返回描述符集合中描述符的数量。失败时,select失败时返回-1,否则返回超时(从底层的select系统调用).
参见 ¶
--------------------------------------------------
while (($code = curl_multi_exec($queue, $active)) == CURLM_CALL_MULTI_PERFORM) ;
相当于
do{
($code = curl_multi_exec($queue, $active)) )
}while($code == CURLM_CALL_MULTI_PERFORM)
==================================================================================
1. 经典cURL并发机制及其存在的问题
经典的cURL实现机制在网上很容易找到, 比如参考PHP在线手册的如下实现方式:
function classic_curl($urls, $delay) {
$queue = curl_multi_init();
$map = array();
foreach ($urls as $url) {
// create cURL resources
$ch = curl_init();
// set URL and other appropriate options
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_TIMEOUT, 1);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_NOSIGNAL, true);
// add handle
curl_multi_add_handle($queue, $ch);
$map[$url] = $ch;
}
$active = null;
// execute the handles 当curl批处理有错误的时候,循环批处理,直到没错误,$active === &$still_running
批处理命令发出后,操作会要等一段时间才能完成,
do {
$mrc = curl_multi_exec($queue, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
while ($active > 0 && $mrc == CURLM_OK) {
if (curl_multi_select($queue, 0.5) != -1) {
do {
$mrc = curl_multi_exec($queue, $active);
} while ($mrc == CURLM_CALL_MULTI_PERFORM);
}
}
$responses = array();
foreach ($map as $url=>$ch) {
$responses[$url] = callback(curl_multi_getcontent($ch), $delay);
curl_multi_remove_handle($queue, $ch);
curl_close($ch);
}
curl_multi_close($queue);
return $responses;
}
2. 改进的Rolling cURL并发方式
仔细分析不难发现经典cURL并发还存在优化的空间, 优化的方式时当某个URL请求完毕之后尽可能快的去处理它, 边处理边等待其他的URL返回, 而不是等待那个最慢的接口返回之后才开始处理等工作, 从而避免CPU的空闲和浪费. 闲话不多说, 下面贴上具体的实现:
function rolling_curl($urls, $delay) {
$queue = curl_multi_init();
$map = array();
foreach ($urls as $url) {
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_TIMEOUT, 1);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_NOSIGNAL, true);
curl_multi_add_handle($queue, $ch);
$map[(string) $ch] = $url;
}
$responses = array();
do {
while (($code = curl_multi_exec($queue, $active)) == CURLM_CALL_MULTI_PERFORM) ;
if ($code != CURLM_OK) { break; }
// a request was just completed -- find out which one
while ($done = curl_multi_info_read($queue)) {
// get the info and content returned on the request
$info = curl_getinfo($done['handle']);
$error = curl_error($done['handle']);
$results = callback(curl_multi_getcontent($done['handle']), $delay);
$responses[$map[(string) $done['handle']]] = compact('info', 'error', 'results');
// remove the curl handle that just completed
curl_multi_remove_handle($queue, $done['handle']);
curl_close($done['handle']);
}
// Block for data in / output; error handling is done by curl_multi_exec
if ($active > 0) {
curl_multi_select($queue, 0.5);
}
} while ($active);
curl_multi_close($queue);
return $responses;
}
改进前后的性能对比试验在LINUX主机上进行, 测试时使用的并发队列如下:
var_dump(rolling_curl(array(
'http://item.jd.com/1120135.html',
'http://item.jd.com/164112.html',
),100));
简要说明下实验设计的原则和性能测试结果的格式: 为保证结果的可靠, 每组实验重复20次, 在单次实验中, 给定相同的接口URL集合, 分别测量Classic(指经典的并发机制)和Rolling(指改进后的并发机制)两种并发机制的耗时(秒为单位), 耗时短者胜出(Winner), 并计算节省的时间(Excellence, 秒为单位)以及性能提升比例(Excel. %). 为了尽量贴近真实的请求而又保持实验的简单, 在对返回结果的处理上只是做了简单的正则表达式匹配, 而没有进行其他复杂的操作. 另外, 为了确定结果处理回调对性能对比测试结果的影响, 可以使用usleep模拟现实中比较负责的数据处理逻辑(如提取, 分词, 写入文件或数据库等).
性能测试中用到的回调函数为:
function callback($data, $delay)
{
preg_match_all('/<h3>(.+)<\/h3>/iU', $data, $matches);
usleep($delay);
return compact('data', 'matches');
}
数据处理回调无延迟时: Rolling Curl略优, 但性能提升效果不明显.
------------------------------------------------------------------------------------------------ Delay: 0 micro seconds, equals to 0 milli seconds ------------------------------------------------------------------------------------------------ Counter Classic Rolling Winner Excellence Excel. % ------------------------------------------------------------------------------------------------ 1 0.1193 0.0390 Rolling 0.0803 67.31% 2 0.0556 0.0477 Rolling 0.0079 14.21% 3 0.0461 0.0588 Classic -0.0127 -21.6% 4 0.0464 0.0385 Rolling 0.0079 17.03% 5 0.0534 0.0448 Rolling 0.0086 16.1% 6 0.0540 0.0714 Classic -0.0174 -24.37% 7 0.0386 0.0416 Classic -0.0030 -7.21% 8 0.0357 0.0398 Classic -0.0041 -10.3% 9 0.0437 0.0442 Classic -0.0005 -1.13% 10 0.0319 0.0348 Classic -0.0029 -8.33% 11 0.0529 0.0430 Rolling 0.0099 18.71% 12 0.0503 0.0581 Classic -0.0078 -13.43% 13 0.0344 0.0225 Rolling 0.0119 34.59% 14 0.0397 0.0643 Classic -0.0246 -38.26% 15 0.0368 0.0489 Classic -0.0121 -24.74% 16 0.0502 0.0394 Rolling 0.0108 21.51% 17 0.0592 0.0383 Rolling 0.0209 35.3% 18 0.0302 0.0285 Rolling 0.0017 5.63% 19 0.0248 0.0553 Classic -0.0305 -55.15% 20 0.0137 0.0131 Rolling 0.0006 4.38% ------------------------------------------------------------------------------------------------ Average 0.0458 0.0436 Rolling 0.0022 4.8% ------------------------------------------------------------------------------------------------ Summary: Classic wins 10 times, while Rolling wins 10 times
数据处理回调延迟5毫秒: Rolling Curl完胜, 性能提升40%左右.
------------------------------------------------------------------------------------------------ Delay: 5000 micro seconds, equals to 5 milli seconds ------------------------------------------------------------------------------------------------ Counter Classic Rolling Winner Excellence Excel. % ------------------------------------------------------------------------------------------------ 1 0.0658 0.0352 Rolling 0.0306 46.5% 2 0.0728 0.0367 Rolling 0.0361 49.59% 3 0.0732 0.0387 Rolling 0.0345 47.13% 4 0.0783 0.0347 Rolling 0.0436 55.68% 5 0.0658 0.0286 Rolling 0.0372 56.53% 6 0.0687 0.0362 Rolling 0.0325 47.31% 7 0.0787 0.0337 Rolling 0.0450 57.18% 8 0.0676 0.0391 Rolling 0.0285 42.16% 9 0.0668 0.0351 Rolling 0.0317 47.46% 10 0.0603 0.0317 Rolling 0.0286 47.43% 11 0.0714 0.0350 Rolling 0.0364 50.98% 12 0.0627 0.0215 Rolling 0.0412 65.71% 13 0.0617 0.0401 Rolling 0.0216 35.01% 14 0.0721 0.0226 Rolling 0.0495 68.65% 15 0.0701 0.0428 Rolling 0.0273 38.94% 16 0.0674 0.0352 Rolling 0.0322 47.77% 17 0.0452 0.0425 Rolling 0.0027 5.97% 18 0.0596 0.0366 Rolling 0.0230 38.59% 19 0.0679 0.0480 Rolling 0.0199 29.31% 20 0.0657 0.0338 Rolling 0.0319 48.55% ------------------------------------------------------------------------------------------------ Average 0.0671 0.0354 Rolling 0.0317 47.24% ------------------------------------------------------------------------------------------------ Summary: Classic wins 0 times, while Rolling wins 20 times
通过上面的性能对比, 在处理URL队列并发的应用场景中Rolling cURL应该是更加的选择, 并发量非常大(1000+)时, 可以控制并发队列的最大长度, 比如20, 每当1个URL返回并处理完毕之后立即加入1个尚未请求的URL到队列中, 这样写出来的代码会更加健壮, 不至于并发数太大而卡死或崩溃. 详细的实现请参考:http://code.google.com/p/rolling-curl/
5. 参考资料和延伸阅读
- Client URL Library http://www.php.net/manual/en/book.curl.php
- Parallel CURL Requests with PHP http://blog.rob.cx/multi-curl
- A more efficient multi-curl library for PHP (non-blocking) http://code.google.com/p/rolling-curl/
- PHP: Parallel cURL Performance http://stackoverflow.com/questions/10485199/php-parallel-curl-performance-rollingcurl-vs-parallelcurl
文章出处:http://www.searchtb.com/2012/06/rolling-curl-best-practices.html