@inproceedings{6a100ccd91be45d19f78609da93d17b4,
title = "ERMS: An elastic replication management system for HDFS",
abstract = "The Hadoop Distributed File System (HDFS) is a distributed storage system that stores large-scale data sets reliably and streams those data sets to applications at high bandwidth. HDFS provides high performance, reliability and availability by replicating data, typically three copies of every data. The data in HDFS changes in popularity over time. To get better performance and higher disk utilization, the replication policy of HDFS should be elastic and adapt to data popularity. In this paper, we describe ERMS, an elastic replication management system for HDFS. ERMS provides an active/standby storage model for HDFS. It utilizes a complex event processing engine to distinguish real-time data types, and then dynamically increases extra replicas for hot data, cleans up these extra replicas when the data cool down, and uses erasure codes for cold data. ERMS also introduces a replica placement strategy for the extra replicas of hot data and erasure coding parities. The experiments show that ERMS effectively improves the reliability and performance of HDFS and reduce storage overhead.",
keywords = "Elastic, HDFS, Replication Management",
author = "Zhendong Cheng and Zhongzhi Luan and You Meng and Yijing Xu and Depei Qian and Alain Roy and Ning Zhang and Gang Guan",
year = "2012",
doi = "10.1109/ClusterW.2012.25",
language = "英语",
isbn = "9780768548449",
series = "Proceedings - 2012 IEEE International Conference on Cluster Computing Workshops, Cluster Workshops 2012",
publisher = "IEEE Computer Society",
pages = "32--40",
booktitle = "Proceedings - 2012 IEEE International Conference on Cluster Computing Workshops, Cluster Workshops 2012",
address = "美国",
note = "2012 IEEE International Conference on Cluster Computing Workshops, Cluster Workshops 2012 ; Conference date: 24-09-2012 Through 28-09-2012",
}