Mapreduce performance model for Hadoop 2.x

作者：

Highlights：

• We identify cost factors that affect the cost of the MapReduce job execution in Hadoop 2.x.

• We build MapReduce Performance model for Hadoop 2.x. and introduce a novel approach for job response time estimation.

• We evaluate the accuracy of our approach through comparing model-based estimations with real MapReduce executions.

摘要

•We identify cost factors that affect the cost of the MapReduce job execution in Hadoop 2.x.•We build MapReduce Performance model for Hadoop 2.x. and introduce a novel approach for job response time estimation.•We evaluate the accuracy of our approach through comparing model-based estimations with real MapReduce executions.

论文关键词：Hadoop 2.x,MapReduce performance model

论文评审过程：Received 14 July 2017, Revised 15 October 2017, Accepted 27 November 2017, Available online 2 December 2017, Version of Record 5 November 2018.

论文官网地址：https://doi.org/10.1016/j.is.2017.11.006