Network-Aware Locality Scheduling for Distributed Data Operators in Data Centers

Journal Article (2021)
Author(s)

Long Cheng (North China Electric Power University, Chinese Academy of Sciences)

Ji Yin Wang (Chinese Academy of Sciences)

Qingzhi Liu (Wageningen University & Research)

D.H.J. Epema (TU Delft - Data-Intensive Systems)

C. Liu (Chinese Academy of Sciences)

Ying Mao (Fordham University)

John Murphy (University College Dublin)

Research Group
Data-Intensive Systems
Copyright
© 2021 Long Cheng, Ying Wang, Qingzhi Liu, D.H.J. Epema, Cheng Liu, Ying Mao, John Murphy
DOI related publication
https://doi.org/10.1109/TPDS.2021.3053241
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 Long Cheng, Ying Wang, Qingzhi Liu, D.H.J. Epema, Cheng Liu, Ying Mao, John Murphy
Research Group
Data-Intensive Systems
Issue number
6
Volume number
32
Pages (from-to)
1494-1510
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Large data centers are currently the mainstream infrastructures for big data processing. As one of the most fundamental tasks in these environments, the efficient execution of distributed data operators (e.g., join and aggregation) are still challenging current data systems, and one of the key performance issues is network communication time. State-of-the-art methods trying to improve that problem focus on either application-layer data locality optimization to reduce network traffic or on network-layer data flow optimization to increase bandwidth utilization. However, the techniques in the two layers are totally independent from each other, and performance gains from a joint optimization perspective have not yet been explored. In this article, we propose a novel approach called NEAL (NEtwork-Aware Locality scheduling) to bridge this gap, and consequently to further reduce communication time for distributed big data operators. We present the detailed design and implementation of NEAL, and our experimental results demonstrate that NEAL always performs better than current approaches for different workloads and network bandwidth configurations.

Files

Neal_IEEE_TPDS_20210125.pdf
(pdf | 0.989 Mb)
License info not available