• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2013, Vol. 35 ›› Issue (10): 125-130.

• 论文 • 上一篇    下一篇

Hadoop平台中空闲时间调度器的设计与实现

杨浩,滕飞,李天瑞,李曌   

  1. (西南交通大学信息科学与技术学院,四川 成都 610031)
  • 收稿日期:2013-06-15 修回日期:2013-09-10 出版日期:2013-10-25 发布日期:2013-10-25
  • 基金资助:

    国家自然科学基金资助项目(61202043,61175047);中央高校基本科研业务费专项资金(SWJTU11ZT08,SWJTU12CX098)

Design and implementation of
a least spare time scheduler for Hadoop       

YANG Hao,TENG Fei,LI Tianrui,LI Zhao   

  1. (School of Information Science and Technology,Southwest Jiaotong University,Chengdu 610031,China)
  • Received:2013-06-15 Revised:2013-09-10 Online:2013-10-25 Published:2013-10-25

摘要:

Hadoop作为开源的云计算平台,被广泛应用于自然语言处理、机器学习、大规模图像处理等领域。随着云计算与各行业广泛而深入的结合,多样化的服务对于时效性要求越来越高。现有的Hadoop调度器多关注于缩短响应时间,而非满足作业的时限要求。为了提高集群处理硬实时作业的性能,设计并实现了一种基于空闲时间的硬实时调度器LSS。在调度过程中,LSS动态估算作业的空闲时间,并据此实时更新作业队列中作业的优先级顺序。实验结果表明LSS能够有效地提高集群处理硬实时作业的成功率。

关键词: 云计算, 实时作业, 调度, 空闲时间

Abstract:

As an open source platform of cloud computing, Hadoop is widely used in many fields, such as natural language processing, machine learning and largescale image processing. With the increase of the types of cloud services, the realtime requirement is strengthened by cloud users. Most existing schedulers are designed to shorten the response time which cannot guarantee a specific deadline. Least Sparetime Scheduler (LSS) is designed and implemented to improve the performance of hard realtime jobs in Hadoop. The spare time is estimated dynamically and the LSS updates the job priority of the job queue in realtime. Experimental results show that the LSS can improve the success ratio of the cluster dealing with hard realtime jobs.

Key words: Hadoop;realtime jobs;scheduling;spare time