Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


osu1276545759.pdf (1.79 MB)

ETD Abstract Container

Abstract Header

Evaluating and Optimizing Indexing Schemes for an Elastic Cache in a Cloud Environment

Shetty, Apeksha Shrinatha
http://rave.ohiolink.edu/etdc/view?acc_num=osu1276545759

Abstract Details

2010, Master of Science, Ohio State University, Computer Science and Engineering.
Cloud computing or utility computing provides virtual servers over the Internet. It is an on-demand service, where the cost directly depends on the consumption. Moreover, it is an elastic service, where a user can demand more or less resources based on the requirements. Our research group developed and implemented a cooperative elastic cache to accelerate query execution by caching intermediate results, in our scientific workflow system, Auspice. This was achieved by enabling fast access to data by storing it in the main memory. The best means to achieve this was by splitting the entire cache among a set of nodes (on our local cluster) and storing it in the main memory of these nodes. This set of nodes would expand or contract based on the cache size. The elasticity property of the Cloud aids this and hence driven by the popularity and suitability of cloud computing we were motivated to implement the cooperative elastic cache on Amazon EC2 cloud. The performance of the elastic cache is directly linked to the indexing scheme used. Hence in the second part of our work, we evaluate the performance of various indexing schemes. We consider Bx-tree, Extensible Hashing and Counting Bloom Filter schemes as they are extensively used in many real world applications and they have disparate structures. We evaluate these schemes on the basis of their time efficiency. Finally, we focus on optimizing the system. Our approach is comprised of making the system as unobtrusive as possible and making it more time efficient. Hence, we try reducing the idle time and this was achieved by pre-loading nodes and multitasking. Thus, we were able to design both a cost and time efficient system.
Gagan Agrawal, PhD (Advisor)
Hakan Ferhatosmanoglu, PhD (Committee Member)
71 p.
Computer Science

Recommended Citations

Citations

  • Shetty, A. S. (2010). Evaluating and Optimizing Indexing Schemes for an Elastic Cache in a Cloud Environment [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1276545759

    APA Style (7th edition)

  • Shetty, Apeksha. Evaluating and Optimizing Indexing Schemes for an Elastic Cache in a Cloud Environment. 2010. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1276545759.

    MLA Style (8th edition)

  • Shetty, Apeksha. "Evaluating and Optimizing Indexing Schemes for an Elastic Cache in a Cloud Environment." Master's thesis, Ohio State University, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=osu1276545759

    Chicago Manual of Style (17th edition)

osu1276545759
1,917
© 2010, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.