MRScheduling: An Effective Technique for Multi-Tenant Meeting Deadline in MapReduce

Zhong Wang; Bo Suo; Zhuo Wang

doi:10.4028/www.scientific.net/AMM.644-650.4482

Paper Titles

Limited Length and Limited Weight Intelligent Cutting System Based on Image Pattern Recognition and Closed Loop Feedback Device
p.4463

Multi-View Video Signal Processing Based on Disparity Estimation
p.4467

A Hybrid SVD-DCT Watermarking Method Used for Halftone Image
p.4473

Research on the Geometric Distortion Auto-Correction Algorithm for Image Scanned
p.4477

MRScheduling: An Effective Technique for Multi-Tenant Meeting Deadline in MapReduce
p.4482

Design of Remote Data Acquisition System Base on ZigBee and GPRS
p.4487

Remote Data Recorder Design Based on Embedded Linux
p.4491

A Secure Lightweight Mutual Authentication for RFID Systems
p.4496

An Improved Directional GVF Snake
p.4501

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650MRScheduling: An Effective Technique for...

MRScheduling: An Effective Technique for Multi-Tenant Meeting Deadline in MapReduce

Abstract:

The multi-tenant jobs scheduling problem based on MapReduce framework has become more and more significant in contemporary society. Existing scheduling approach or algorithm no longer fit well in scenario that numerous jobs were submitted by multiple users at the same time. Therefore, taken enlarging jobs’ throughput for MapReduce into account, we firstly propose an MRScheduling which focuses on meeting job’s respective deadline. Considering the various parameters which are related to job execution time of a MapReduce’s job, we present a simply time-cost model, for the aim that quantifying the number of job’s assigned map slots and reduce slots. Then, an MRScheduling algorithm is discussed in details. Finally, we perform our approach on both real data and synthetic data on real distributed cluster to verify its effectiveness and efficiency.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

4482-4486

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.4482

Citation:

Cite this paper

Online since:

September 2014

Authors:

Zhong Wang*, Bo Suo, Zhuo Wang

Keywords:

MapReduce, Meet Deadline, Multi-Tenant, Scheduler

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Dean, Jeffrey, and Sanjay Ghemawat. MapReduce: simplified data processing on large clusters., Communications of the ACM 51. 1 (2008): 107-113.

DOI: 10.1145/1327452.1327492

Google Scholar

[2] MapReduce: A Flexible Data Processing Tool.

Google Scholar

[3] Bryant R E. Data-Intensive Supercomputing: the Case for DISC[R].

Google Scholar

[4] Nykiel T, Potamias M, Mishra C, et al. MRShare: sharing across multiple queries in MapReduce[J]. Proceedings of the VLDB Endowment, 2010, 3(1-2): 494-505.

DOI: 10.14778/1920841.1920906

Google Scholar

[5] Ghemawat S, Gobioff H, Leung S T. The Google file system[C]/ACM SIGOPS Operating Systems Review. ACM, 2003, 37(5): 29-43.

DOI: 10.1145/1165389.945450

Google Scholar

[6] Kc K, Anyanwu K. Scheduling hadoop jobs to meet deadlines[C]/Cloud Computing Technology and Science (CloudCom), 2010 IEEE Second International Conference on. IEEE, 2010: 388-392.

DOI: 10.1109/cloudcom.2010.97

Google Scholar

[7] Lin X, Lu Y, Deogun J, et al. Real-time divisible load scheduling for cluster computing[C]/Real Time and Embedded Technology and Applications Symposium, 2007. RTAS'07. 13th IEEE. IEEE, 2007: 303-314.

DOI: 10.1109/rtas.2007.29

Google Scholar