Memcache的mutex设计模式 -- 高并发解决方案

场景

Mutex主要用于有大量并发访问并存在cache过期的场合，如

• 首页top 10, 由数据库加载到memcache缓存n分钟；
• 微博中名人的content cache, 一旦不存在会大量请求不能命中并加载数据库；
• 需要执行多个IO操作生成的数据存在cache中, 比如查询db多次；

问题

在大并发的场合，当cache失效时，大量并发同时取不到cache，会同一瞬间去访问db并回设cache，可能会给系统带来潜在的超负荷风险。我们曾经在线上系统出现过类似故障。

解决方法 

方法一

高并发时，增加data_lock信号标识，只充许一个用户update cache，在cache数据期间，其它并发用户等待，只到这个用户cache成功，当然这个地方需要设置最大等待时间，毕竟当很长时间cache不成功时，不能让用户一直等待:

<?php
function get_my_data2(){
	$cache_id = "mykey";
	$data = $memcache_obj->get($cache_id);
	if (!$data) {
		// check to see if someone has already set the lock
		$data_lock = $memcache_obj->get($cache_id . '_qry_lock');
		if ($data_lock) {
			$lock_counter = 0;

			// loop until you find that the lock has been released. that implies that the query has finished
			while ($data_lock) {
				// you may only want to wait for a specified period of time.
				// one second is usually sufficient since your goal is to always have sub-second response time
				// if you query takes more than 1 second, you should consider "warming" your cached data via a cron job
				if ($lock_counter > $max_time_to_wait) {
					$lock_failed = true;
					break;
				}

				// you really want this to be a fraction of a second so the user waits as little as possible
				// for the simplicity of example, I'm using the sleep function.
				sleep(1);
				$data_lock = $memcache_obj->get($cache_id . '_qry_lock');
			}

			// if the loop is completed, that either means the user waited for too long
			// or that the lock has been removed.  try to get the cached data again; it should exist now
			$data = $memcache_obj->get($cache_id);
			if ($data) {
				return $data;
			}
		}

		// set a lock for 2 seconds
		$memcache_obj->set($cache_id . '_qry_lock', true, 2);
		$data = get_data_from_db_function();
		$memcache_obj->set($cache_id, $data, $sec_to_cache_for);

		// don't forget to remove the lock
		$memcache_obj->delete($cache_id . '_qry_lock');
	}

	return $data;
}

方法二 

需要给数据增加一个cache过期时间标识，高并发时，在用户取数据时，检查cache是否快要过期，如果即将过期，则充许一个用户去更新cache，其它用户依然访问没有update的数据。

<?php
function get_my_data3() {
	$cache_id = "mykey";
	$data = $memcache_obj->get($cache_id);

	// if there is cached data and the expire timestamp has already expired or is within the next 2 minutes
	// then we want the user to freshen up the cached data
	if ($data && ($data['cache_expires_timestamp'] - time()) < 120) {
		// if the semaphore lock has already been set, just return the data like you normally would.
		if ($memcache_obj->get($cache_id . '_expire_lock')) {
			return $data;
		}

		// now we want to set the lock and have the user freshen the data.
		$memcache_obj->set($cache_id . '_expire_lock', true, 2);

		// by unsetting the data it will cause the data gather logic below to execute.
		unset($data);
	}

	if (!$data) {
		// be sure to include all of the semaphore logic from example 2

		// set the _qry_lock for 2 seconds
		$memcache_obj->set($cache_id . '_qry_lock', true, 2);
		$raw_data = get_data_from_db_function();
		$data['cache_expires_timestamp'] = time() + $sec_to_cache_for;
		$data['cached_data'] = $raw_data;
		$memcache_obj->set($cache_id, $data, $sec_to_cache_for);

		// remove the _qry_lock
		$memcache_obj->delete($cache_id . '_qry_lock');

		// remove the _expires_lock
		$memcache_obj->delete($cache_id . '_expires_lock');
	}

	return $data;
}

---

项目中的一个缓存类参考：

CacheModel.class.php

<?php
namespace framework;
use framework\Cache;

/**
 * 缓存模型 - 业务逻辑模型
 *
 * @example
 * setType($type)					主动设置缓存类型
 * set($key, $value, $expire = 0)	设置缓存key=>value，expire表示有效时间，0表示永久
 * get($key, $mutex = false)		获取缓存数据，支持mutex模式
 * getList($prefix, $key)			批量获取指定前缀下的多个key值的缓存
 * rm($key)							删除缓存
 */
class CacheModel {
	protected $config = array();		// 缓存配置文件
	protected $handler = null;			// 当前缓存操作对象
	protected $type = '';				// 当前缓存类型

	/**
	 * 取得缓存类实例
	 *
	 * @param array $config 缓存节点
	 * @return mixed 返回类实例
	 */
	public static function getInstance($connection = 'default') {
		static $_instance = null;

		if (!isset($_instance)) {
			$_instance = new self($connection);
		}

		return $_instance;
	}

	/**
	 * 初始化缓存模型对象，缓存类型
	 *
	 * @return void
	 */
	public function __construct($connection = '') {
		$this->_initHandler($connection);
	}

	/**
	 * 初始化配置文件
	 */
	private function _initHandler($connection = '') {
		// 获取缓存配置信息
		$connection = $connection ? $connection : 'default';
		if (!isset($this->config[$connection])) {
			$this->config[$connection] = array_merge(get_config('cache/__common__'), get_config('cache/' . $connection));
		}

		$this->type = strtolower($this->config[$connection]['type']);
		$this->handler = Cache::getInstance($this->config[$connection]);
	}

	/**
	 * 链式设置缓存节点
	 *
	 * @param string $type 缓存类型
	 * @return object 缓存模型对象
	 */
	public function setConnection($connection = '') {
		$this->_initHandler($connection);
		return $this;
	}

	/**
	 * 设置缓存
	 *
	 * @param string $key 缓存Key值
	 * @param mix $value 缓存Value值
	 * @param int $expire  有效时间（单位：秒，0表示永不过期）
	 * @param boolean 是否设置成功
	 */
	public function set($key, $value, $expire = 0) {
		$value = array(
			'cache_data' => $value,		// 缓存数据
			'cache_mtime' => time(),	// 缓存修改时间戳
			'cache_expire' => is_null($expire) ? 0 : intval($expire) // 缓存有效时间
		);

		return $this->handler->set($key, $value);
	}

	/**
	 * 获取缓存操作，支持mutex模式
	 * mutex使用注意
	 * 1.设置缓存(set)时，需要设置有效时间
	 * 2.获取缓存(get)时，需要主动创建缓存
	 *
	 * @param string $key 缓存Key值
	 * @param boolean $mutex 是否启用mutex模式，默认启用
	 * @return mix 缓存数据
	 */
	public function get($key, $mutex = true) {
		// 静态缓存
		$sc = get_static('cache_model_' . $key);
		if (isset($sc)) {
			return $sc;
		}

		// 获取缓存数据
		$data = $this->handler->get($key);

		// 未成功取到缓存
		if ($data === false) {
			return false;
		}

		// 未过期
		if (($data ['cache_expire'] === 0) || (($data ['cache_mtime'] + $data ['cache_expire']) > time ())) {
			return $this->_returnData($data['cache_data'], $key);
		}

		// 已过期
		if ($mutex) { // mutex模式开启
			$data['cache_mtime'] = time();
			$this->handler->set($key, $data);

			// 返回false，让调用程序去主动更新缓存
			set_static('cache_model_' . $key, null);

			return false;
		} else { // mutex模式没开启
			$this->rm($key);
			return false;
		}
	}

	/**
	 * 删除缓存
	 *
	 * @param string $_key 缓存Key值
	 * @return boolean 是否删除成功
	 */
	public function rm($key) {
		set_static('cache_model_' . $key, null);
		return $this->handler->rm($key);
	}

	/**
	 * 清除缓存
	 *
	 * @access public
	 * @return boolen
	 */
	public function clear() {
		return $this->handler->clear();
	}

	/**
	 * 根据某个前缀，批量获取多个缓存
	 *
	 * @param string $prefix 缓存前缀
	 * @param string $keys 缓存Keys值
	 * @return mix 缓存数据
	 */
	public function getList($prefix = '', $keys = array()) {
		if ($this->type == 'memcache') {
			// Memcache有批量获取缓存的接口
			$_data = $this->handler->getMulti($prefix, $keys);
			if ($_data) {
				foreach ($_data as $key => $val) {
					$data[$key] = $this->_returnData($val['cache_data'], $prefix . $key);
				}
			}
		} else {
			foreach ($keys as $key) {
				$_k = $prefix . $key;
				$data[$key] = $this->get($_k);
			}
		}

		return $data;
	}

	/**
	 * 返回缓存数据操作，方法中，将数据缓存到静态缓存中
	 *
	 * @param mix $data 缓存数据
	 * @param string $key 缓存Key值
	 * @return mix 缓存数据
	 */
	private function _returnData($data, $key) {
		set_static('cache_model_' . $key, $data);
		return $data;
	}
}

参考：

memcached PHP semaphore & cache expiration handling

[Tim]Memcache mutex设计模式