An Analysis of Utilization on Virtualized Computing Resource for Hadoop and HBase based Big Data Processing Applications

Hadoop과 HBase 기반의 빅 데이터 처리 응용을 위한 가상 컴퓨팅 자원 이용률 분석

  • Cho, Nayun (Computer Engineering, Konkuk University) ;
  • Ku, Mino (Computer Engineering, Konkuk University) ;
  • Kim, Baul (Computer Engineering, Konkuk University) ;
  • Xuhua, Rui (Computer Engineering, Konkuk University) ;
  • Min, Dugki (Computer Engineering, Konkuk University)
  • 조나연 (건국대학교 대학원 컴퓨터.정보통신공학과) ;
  • 구민오 (건국대학교 대학원 컴퓨터.정보통신공학과) ;
  • 김바울 (건국대학교 대학원 컴퓨터.정보통신공학과) ;
  • ;
  • 민덕기 (건국대학교 대학원 컴퓨터.정보통신공학과)
  • Received : 2014.11.07
  • Accepted : 2014.12.30
  • Published : 2014.12.30

Abstract

In big data era, there are a number of considerable parts in processing systems for capturing, storing, and analyzing stored or streaming data. Unlike traditional data handling systems, a big data processing system needs to concern the characteristics (format, velocity, and volume) of being handled data in the system. In this situation, virtualized computing platform is an emerging platform for handling big data effectively, since virtualization technology enables to manage computing resources dynamically and elastically with minimum efforts. In this paper, we analyze resource utilization of virtualized computing resources to discover suitable deployment models in Apache Hadoop and HBase-based big data processing environment. Consequently, Task Tracker service shows high CPU utilization and high Disk I/O overhead during MapReduce phases. Moreover, HRegion service indicates high network resource consumption for transfer the traffic data from DataNode to Task Tracker. DataNode shows high memory resource utilization and Disk I/O overhead for reading stored data.

빅 데이터 시대에서 데이터를 획득하고 저장하며 실시간으로 유입되거나 저장 된 데이터를 분석하는 처리 시스템은 다양한 부분을 고려해야 한다. 기존의 데이터 처리 시스템들과는 상이하게 빅 데이터 처리 시스템들에서는 시스템 내에서 처리될 데이터들의 포맷, 유입 속도, 크기 등의 특성을 고려해야한다. 이러한 상황에서, 가상화된 컴퓨팅 플랫폼은 가상화 기술로써 컴퓨팅 자원들을 동적이고 신축적으로 관리할 수 있음에 따라, 빅 데이터를 효율적으로 처리하기 위해 급부상하고 있는 플랫폼 중 하나이다. 본 논문에서는 가상화 된 컴퓨팅 플랫폼 상에서 Apache Hadoop과 HBase 기반의 빅 데이터처리 미들웨어를 구동하기 위하여 적합한 배포 모델을 위한 가상 컴퓨팅 자원 이용률을 분석하였다. 본 연구 결과, Task Tracker 서비스는 처리 중 높은 CPU 자원 활용율과 중간 결과물 저장 시점에서는 비교적 높은 디스크 I/O 사용을 보였다. 또한 HRegion 서비스의 경우, DataNode와의 데이터 교환을 위한 네트워크 자원 활용 비율이 높았으며, DataNode 서비스는 I/O 집약적인 처리 패턴을 보였다.

Keywords

Acknowledgement

Supported by : 정보통신산업진흥원

References

  1. S. Madden, "From Databases to Big Data," IEEE Internet Computing, Vol. 16, No. 3, pp. 4-6, 2012.
  2. Ku, M. and Ku, M., "Are We Ready for the Era of Big Data?," The 2014 Association for Public Policy Analysis and Management Conference (APPAM), Apr. 2014.
  3. Kaisler, S., Armour, F., Espinosa, J. A., and Money, W., "Big Data: Issues and Challenges Moving Forward," 46th Hawaii International Conference on System Sciences (HICSS), Jan, 2013, pp. 995-1004.
  4. Russom, P., "Big data analytics," TDWI Best Practices Report, 4th Quarter 2011.
  5. Hseush, W., Yi-Cheng Huang, Shih-Chang Hsu, and Pu, C., "Real-time collaborative planning with big data: Technical challenges and in-place computing (invited paper)," 2013 9th International Conference on Collaborative Computing: Networking, Applications and Worksharing, Oct, 201, pp. 96- 104.
  6. Big Data Analytics, Gartner, Jan. 2011.
  7. V. R. Borkar, M. J. Carey, and C. Li, "Big data platforms: what's next?," ACM Crossroads, Vol. 19, No. 1, pp. 44-49, 2012. https://doi.org/10.1145/2331042.2331057
  8. R. E. Bryant, R. H. Katz, and E. D. Lazowska, "Bigdata Computing: Creating Revolutionary Breakthroughs in Commerce, Science, and society," Computing Research Initiatives for the 21st Century, Computing Research Association, 2008. pp. 1-15.
  9. Apache Hadoop, http://hadoop.apache.org/.
  10. Apache Hadoop, http://hbase.apache.org/.
  11. Bakshi, K., "Considerations for big data: Architecture and approach," International Conference on Aerospace, IEEE Publisher, March, 2012, pp. 1-7.
  12. R. Taylor, "An overview of the Hadoop/MapReduce/ HBase framework and its current applications in bioinformatics," BMC Bioinformatics 11(Suppl 12): S1, 2010.
  13. Padhy R P., "Big Data Processing with Hadoop- MapReduce in Cloud Systems," International Journal of Cloud Computing and Services Science, Vol. 2, No. 1, pp. 16-27, 2012.
  14. Jeongrae Kim and Chanki Jeong, "A Study on Phon Call Big Data Analytics," Journal of Information Technology and Architecture, Vol. 10, No. 3, pp. 387-397, 2013.
  15. Suan Lee, Sunhwa Jo and Jinho Kim, "An Iterative Algorithm for the Bottom Up Computation of the Data Cube using MapReduce," Journal of Information Technology and Architecture, Vol. 9, No. 4, pp. 455-464, 2012.
  16. D. Agrawal, S. Das, and A. E. Abbadi., "Big Data and Cloud Computing: New Wine or just New Bottles?," The Proceedings of the VLDB Endowment (PVLDB), Vol. 3, No. 2, pp. 1647-1648, 2010.
  17. S. Tsuchiya, Y. Sakamoto, Y. Tsuchimoto, and V. Lee, "Big data processing in Cloud environments," FUJITSU SCIENTIFIC & TECHNICAL JOURNAL, Vol. 48, No. 2, pp. 159-168, 2012.
  18. S. Chaudhuri, "What Next? A Half-Dozen Data Management Research Goals for Big Data and the Cloud," The 31st Symposium on Principles of Database Systems (PODS), ACM, 2012, pp. 1-4.
  19. J. Schad, J. Dittrich, and J.-A. Quiane-Ruiz., "Runtime Measurements in the Cloud: Observing, Analyzing, and Reducing Variance," The Proceedings of the VLDB Endowment (PVLDB), Vol. 3, No. 1, 2010.
  20. J. Varia. Architecting for the cloud: Best practices. Technical report, Amazon, 2011.
  21. W. Lloyd, S. Pallickara, O. David, J. Lyon, M. Arabi, and K. Rojas, "Performance Implications of Multi-tier Application Deployments on Infrastructureas- a-service Clouds: Towards Performance Modeling," Future Generation Computer Systems, Vol. 29, No. 5, pp. 1254-1264, 2012.
  22. J. Dean,, and S. Ghemawat, "MapReduce: Simplified data processing on large clusters," The 6th Symposium on Operating System Design and Implementation, 2004, pp. 10-10.
  23. Amaznon Elastic MapReduce, http://aws.amazon. com/ko/elasticmapreduce/.
  24. E. Feller, L. Ramakrishnan, and C. Morin, "On the performance and energy efficiency of Hadoop deployment models," International Conference on Big Data, Oct, 2013, pp. 131-136.
  25. Mino Ku, Eunmi Choi, and Dugki Min, "An analysis of performance factors on Esper-based stream big data processing in a virtualized environment," International Journal of Communication Systems, Vol. 27, No. 6, pp. 898-917, 2014. https://doi.org/10.1002/dac.2734
  26. TASAS, California Department of Transportation, http://www.dot.ca.gov/
  27. PeMS, California Department of Transportation, http://pems.dot.ca.gov/
  28. Yeo H, Jang K, Skabardonis A, Kang S., "Impact of traffic states on freeway crash involvement rates," Accident Analysis and Prevention, Elsevier, Vol. 50, Jan, 2013, pp. 713-723. https://doi.org/10.1016/j.aap.2012.06.023
  29. White T, Hadoop: The Definitive Guide, O'Reilly Media, 2009.
  30. Lars George, HBase: The Definitive Guide, O'Reilly Media, 2011.