H-word: Supporting job scheduling in Hadoop with workload-driven data redistribution
Document typeConference report
Rights accessOpen Access
Today’s distributed data processing systems typically follow a query shipping approach and exploit data locality for reducing network traffic. In such systems the distribution of data over the cluster resources plays a significant role, and when skewed, it can harm the performance of executing applications. In this paper, we addressthe challenges of automatically adapting the distribution of data in a cluster to the workload imposed by the input applications. We propose a generic algorithm, named H-WorD, which, based on the estimated workload over resources, suggests alternative execution scenarios of tasks, and hence identifies required transfers of input data a priori, for timely bringing data close to the execution. We exemplify our algorithm in the context of MapReduce jobs in a Hadoop ecosystem. Finally, we evaluate our approach and demonstrate the performance gains of automatic data redistribution.
The final publication is available at http://link.springer.com/chapter/10.1007/978-3-319-44039-2_21
CitationJovanovic, P., Romero, O., Calders, T., Abello, A. H-word: Supporting job scheduling in Hadoop with workload-driven data redistribution. A: Conference on Advances in Databases and Information Systems. "Advances in Databases and Information Systems - 20th East European Conference, ADBIS 2016, Proceedings". Praga: 2016, p. 306-320.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder