Energy aware colocation of workload in data centers

Author

Pore, Madhurima ; Abbasi, Zeinab ; Gupta, Sandeep K. S. ; Varsamopoulos, Georgios

Author_Institution

Sch. of Comput., Inf. & Decision Syst. Eng., Impact Lab., Tempe, AZ, USA

fYear

2012

fDate

18-22 Dec. 2012

Firstpage

1

Lastpage

6

Abstract

There exists an interference due to colocating applications which depends on the applications´ workload types, degrades the performance and affects the energy consumption of applications. We hypothesize the interference energy consumption and model it as “interference coefficient” and use it to develop an application-aware colocation management policy to colocate the applications in data centers. Including the interference effect in simulations using synthetic workload in the colocation management policy results energy savings of up to 8%.

Keywords

computer centres; power aware computing; resource allocation; application colocation; application energy consumption; application workload type; application-aware colocation management policy; data center; energy aware workload colocation; energy savings; interference coefficient; interference energy consumption; Energy efficient colocation; energy proportionality and Data center energy efficiency;

fLanguage

English

Publisher

ieee

Conference_Titel

High Performance Computing (HiPC), 2012 19th International Conference on

Conference_Location

Pune

Print_ISBN

978-1-4673-2372-7

Electronic_ISBN

978-1-4673-2370-3

Type

conf

DOI

10.1109/HiPC.2012.6507527

Filename

6507527