A cost-effective approach to improving performance of big genomic data analyses in clouds

详细信息    查看全文

• 作者：Christopher Smowton^a ; ^{christopher.smowton@cruk.manchester.ac.uk" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Andoena Balla^b ; ^{andoena@cs.ucy.ac.cy" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Demetris Antoniades^b ; ^{danton@cs.ucy.ac.cy" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Crispin Miller^a ; ^{crispin.miller@cruk.manchester.ac.uk" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; George Pallis^b ; ^{gpallis@cs.ucy.ac.cy" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Marios D. Dikaiakos^b ; ^{mdd@cs.ucy.ac.cy" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Wei Xing^a ; ^{Wei.Xing@manchester.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; ^{wei.xing@cruk.manchester.ac.uk" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Big data ; Clouds ; Performance
• 刊名：Future Generation Computer Systems
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：67
• 期：Complete
• 页码：368-381
• 全文大小：1150 K

文摘

With the rapidly growing demand for DNA analysis, the need for storing and processing large-scale genome data has presented significant challenges. This paper describes how the Genome Analysis Toolkit (GATK) can be deployed to an elastic cloud, and defines policy to drive elastic scaling of the application. We extensively analyse the GATK to expose opportunities for resource elasticity, demonstrate that it can be practically deployed at scale in a cloud environment, and demonstrate that applying elastic scaling improves the performance to cost tradeoff achieved in a simulated environment.