Toward Enhancing Block I/O Performance for Virtualized Hadoop Cluster

Author

Byeong-Moon Ko ; Joonwon Lee ; Heeseung Jo

Author_Institution

Coll. of Inf. & Commun. Eng., Sungkyunkwan Univ. (SKKU), Suwon, South Korea

fYear

2014

fDate

8-11 Dec. 2014

Firstpage

481

Lastpage

482

Abstract

Virtualization offers many advantages by providing server consolidation, isolation, and live migration. In cloud computing environments, virtual machine monitor is an essential part for efficient management of physical resources. Recently, processing big data is important to both most cloud service providers and users. In this paper, the performance of Xen based Hadoop cluster is analyzed, especially related to block device I/O. In addition, the overhead transferring I/O requests are introduced with Xen I/O ring mechanism, and the experimental result of our optimization for Hadoop workloads is presented. The proposed approach reduces CPU utilization by a third during I/O operations and improve throughput of Hadoop applications.

Keywords

cloud computing; parallel processing; virtual machines; Xen I/O ring mechanism; Xen based Hadoop cluster; block I/O performance; cloud computing; live migration; server consolidation; virtual machine monitor; virtualization; Cloud computing; Educational institutions; Linux; Performance evaluation; Throughput; Virtual machine monitors; Virtualization; Block I/O; Hadoop; Para Virtualization; Xen;

fLanguage

English

Publisher

ieee

Conference_Titel

Utility and Cloud Computing (UCC), 2014 IEEE/ACM 7th International Conference on

Conference_Location

London

Type

conf

DOI

10.1109/UCC.2014.61

Filename

7027528