Journal of East China Normal University(Natural Sc

Previous Articles     Next Articles

Sorting algorithm analysis of distributed data based on Map/Reduce

YU Sheng-jun, GONG Xue-qing, ZHU jun, QIAN Wei-ning   

  1. Institute for Data Science and Engineering, East China Normal University, Shanghai 200062, China
  • Received:2016-06-27 Online:2016-09-25 Published:2016-11-29

RichHTML

8

PDF

920

Abstract:

Distributed system has been widely applied in recent years to tackle the storage and calculation of big data. Sorting of large-scale dataset in the distributed system has become the fundamental problem to affect a varieties of application performances which is not only concerning about the selection of sorting algorithm at each node, but also about the development of distributed algorithms to coordinate at each node. This paper summarizes the common distributed sorting algorithms which are applied in the distributed system. Analysis has been conducted to the implementation process, cost model and applicable field of each algorithm. And the analysis results have been verified by experiments. This work can help developers choose and optimize the big data sorting
algorithm in distributed environments.

Key words: distributed system, sorting algorithm, cost model