Title :
Achieving elasticity for cloud MapReduce jobs
Author :
Salah, Khaled ; Alcaraz Calero, Jose M.
Author_Institution :
Electr. & Comput. Eng. Dept., Khalifa Univ. of Sci., Technol. & Res. (KUSTAR), Sharjah, United Arab Emirates
Abstract :
These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute- and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.
Keywords :
Big Data; cloud computing; parallel programming; queueing theory; MapReduce programming framework; SLO response time; analytical queueing model; big data analytics; cloud MapReduce jobs; cloud clusters; cloud computing paradigm; elasticity; large-scale compute-intensive applications; large-scale data-intensive applications; mappers; reducers; service level objective response time; workload conditions; Analytical models; Cloud computing; Computational modeling; Conferences; Elasticity; Random variables; Time factors; Cloud Computing; Elasticity; MapReduce; Netwrok and Sevice Delays; Performance; Queueing Analysis;
Conference_Titel :
Cloud Networking (CloudNet), 2013 IEEE 2nd International Conference on
Conference_Location :
San Francisco, CA
DOI :
10.1109/CloudNet.2013.6710577
