@inproceedings{af8c9b012daa459d99e80b67f6f757d1,
title = "Towards quantitative analysis of data intensive computing: A case study of Hadoop",
abstract = "In modern data centers, Hadoop has been widely used in perform data-intensive computation. Administrators of large scale hadoop clusters leverage statistical data collected at runtime to measure the efficiency of the cluster utilization. In this paper, we propose three statistical metrics - data locality ratio, load balance coefficient and access balance coefficient to quantify performance losses in data intensive applications. We evaluated our metrics using a large scale web click stream application running on a productive hadoop cluster at Tencent Inc.",
keywords = "Hadoop, MapReduce, management, performance metrics",
author = "Peng Wang and Dan Meng and Zhaoxia Han and Xu Liu",
year = "2011",
doi = "10.1145/1998582.1998624",
language = "English",
isbn = "9781450306072",
series = "Proceedings of the 8th ACM International Conference on Autonomic Computing, ICAC 2011 and Co-located Workshops",
pages = "193--194",
booktitle = "Proceedings of the 8th ACM International Conference on Autonomic Computing, ICAC 2011 and Co-located Workshops",
note = "8th ACM International Conference on Autonomic Computing, ICAC 2011 and Co-located Workshops ; Conference date: 14-06-2011 Through 18-06-2011",
}