作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 体系结构与软件技术 • 上一篇    下一篇

P2P多线程动态容错模型的研究与应用

汪建军,于 策,孙济洲,孙 超,金 舟,成 钢   

  1. (天津大学计算机科学与技术学院,天津 300072)
  • 收稿日期:2012-04-26 出版日期:2013-09-15 发布日期:2013-09-13
  • 作者简介:汪建军(1987-),男,硕士研究生,主研方向:分布式并行处理,并行程序设计;于 策(通讯作者),讲师、博士;孙济洲,教授、博士、博士生导师;孙 超,硕士;金 舟,博士;成 钢,博士研究生
  • 基金资助:
    国家自然科学基金资助项目(10978016,11003027);天津市科技支撑计划基金资助重点项目(11ZCKFGX01000, 11ZCKFGX 04200)

Research and Application of P2P Multithread Dynamic Fault-tolerance Model

WANG Jian-jun, YU Ce, SUN Ji-zhou, SUN Chao, JIN Zhou, CHENG Gang   

  1. (School of Computer Science and Technology, Tianjin University, Tianjin 300072, China)
  • Received:2012-04-26 Online:2013-09-15 Published:2013-09-13

摘要: 在多线程并行程序中,如只由主线程负责容错处理,主线程本身则成为潜在的单点故障点。针对该问题,设计一种对等多线程动态容错模型。该模型包含多轮容错过程,每轮容错过程采用容错控制线程随机决定容错模型动态生成的方法。在EasyPDP系统中进行实际应用测试,结果证明,该容错模型能够避免主线程单点故障,同时保证系统加速比与负载平衡性能。

关键词: 多线程, 容错, 单点故障, 对等, EasyPDP系统

Abstract: In a multithread parallel program, the master thread is an underlying single point failure under the consumption that the fault-tolerance is handled by the mast thread only. To solve this problem, a Peer-to-Peer(P2P) multithread dynamic fault-tolerance model is designed and implemented. It contains several rounds of fault-tolerance process, fault-tolerance control thread is decided randomly and the fault-tolerance model is generated dynamically in every round. Test work is conducted in the system of EasyPDP, and results shows that this model is able to avoid the single point failure of the master thread, as well as maintain the system speed-up ratio and load balance performance.

Key words: multithread, fault-tolerance, single point failure, Peer-to-Peer(P2P), EasyPDP system

中图分类号: