Efficiency Experiments on Hadoop and Giraph with PageRank

2016 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP) Pub Date : 2016-04-04 DOI:10.1109/PDP.2016.49

Arne Koschel, Felix Heine, Irina Astrova, Fred Korte, Thomas Rossow, Sebastian Stipkovic

引用次数: 7

Abstract

This paper compares the efficiency of two implementations of the PageRank algorithm, one using Hadoop's MapReduce and the other Giraph's Pregel. The implementations are evaluated against CPU usage, CPU I/O wait time, memory usage, and execution time. The result of the evaluation is that Giraph outperforms Hadoop.

查看原文本刊更多论文

PageRank在Hadoop和Giraph上的效率实验

本文比较了两种实现PageRank算法的效率，一种是使用Hadoop的MapReduce，另一种是使用Giraph的Pregel。根据CPU使用情况、CPU I/O等待时间、内存使用情况和执行时间对实现进行评估。评估的结果是，Giraph优于Hadoop。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2016 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)

自引率

0.00%

发文量