基于消息传递的系统调用优化  

System call optimization with message-passing

作　　者：陈渝[1] 王乃峥[1] 崔岩[1] 

机构地区：[1]清华大学计算机科学与技术系,北京100084

出　　处：《清华大学学报（自然科学版）》2012年第12期1764-1768,共5页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金面上项目(61170050)

摘　　要：多线程编程模型由于能够充分地利用多核系统的硬件资源而被广泛地应用于软件的设计过程。在Intel 40核系统上的测试表明,现在的基于共享内存的操作系统很难对大规模的硬件资源进行有效的管理。特别是当多线程应用程序频繁使用系统提供各种服务时,操作系统的可扩展性将会严重影响应用程序自身的性能。该文将消息传递的思想引入到现有的Linux系统中来,提出一种优化的系统调用机制。这种机制通过动态调整系统调用执行过程来减少多核之间竞争发生的开销。测试表明:该方法能够显著提升多线程系统服务密集型应用在多核系统上的性能和可扩展性。Multithreaded programming is becoming increasingly popular in software design to effectively use the computing resources of multicore systems. Tests on an Intel 40-core system show that current commodity operating systems are not well suited to manage such large scale hardware resources. In particular, the application performance is significantly affected when system services are frequently accessed. This paper describes a message passing mechanism in a Linux kernel with optimization of the system calls that dynamically adjusts execution of the system calls to reduce resource contention overhead. Tests on haekbench and dbeneh show that this method given high performance and sealability for muhithreaded system service intensive applications.

关 键 词：分时操作系统 多核系统 用户态多线程 系统调用 消息传递 

分 类 号：TP316.1[自动化与计算机技术—计算机软件与理论]