分布式的缓存系统 Memcached 1.4.15 发布

   <p><strong>今天发布1.4.15，<a href="/misc/goto?guid=4958184338198183602" target="_blank">memcached</a></strong>是Memcached 是一个高性能的分布式内存对象缓存系统，用于动态Web应用以减轻数据库负载。它通过在内存中缓存数据和对象来减少读取数据库的次数。</p>    <p>memcached具有多种语言的客户端开发包，包括：Perl/PHP/JAVA/C/Python/Ruby/C#/MySQL/<br /> </p>    <p></p>    <p>下载地址： <a href="/misc/goto?guid=4958523538498999775" target="_blank"><strong>http://memcached.googlecode.com/files/memcached-1.4.15.tar.gz</strong></a></p>    <p><strong>此版本增强了多线程下的读写性能。</strong></p>    <h2>修复情况</h2>    <ul>     <li>Add some mild thread documentation </li>     <li>README.md was missing from dist tarball </li>     <li><a class="closed_ref" title="'--disable-coverage drops " href="/misc/goto?guid=4958523538617180718" option??="" -pthread?=""> Issue 286 </a>: --disable-coverage drops "-pthread" option </li>     <li>Reduce odds of getting OOM errors in some odd cases </li>    </ul>    <h2><a name="New_Features"></a>新的特性：</h2>    <p>Thread scalability is much improved for reads, and somewhat improved for writes. In a pure read-only situation on a dual socket six core NUMA machine I've tested key fetch rates around 13.6 million keys per second.</p>    <p>More tuning is necessary and you'd get significant lag at that rate, but that shows the theoretical limit of the locks.</p>