EPOBF: Energy Efficient Allocation of Virtual Machines in High Performance Computing Cloud - Transactions on Large-Scale Data-and Knowledge-Centered Systems - page 71

EPOBF: Energy E cient Allocation
of Virtual Machines in High Performance
Computing Cloud

B

Nguyen Quang-Hung (

) , Nam Thoai, and Nguyen Thanh Son

Faculty of CSE, HCMC University of Technology, VNUHCM,
268 Ly Thuong Kiet Street, Ho Chi Minh City, Vietnam
{ hungnq2,nam,sonsys } @cse.hcmut.edu.vn

Abstract. Cloud computing has become more popular in provision of
computing resources under virtual machine (VM) abstraction for high
performance computing (HPC) users. A HPC cloud is such a cloud com-
puting environment. One of the challenges of energy-ecient resource
allocation of VMs in HPC clouds is the trade-off between minimiz-
ing total energy consumption of physical machines (PMs) and satis-
fying Quality of Service (e.g. performance). On the one hand, cloud
providers want to maximize their profit by reducing the power cost
(e.g. using the smallest number of running PMs). On the other hand,
cloud customers (users) want highest performance for their applications.
In this paper, we study energy-ecient allocation of VMs that focuses
on scenarios where users request short-term resources at fixed start-
times and non-interrupted durations. We then propose a new alloca-
tion heuristic (namely Energy-aware and Performance-per-watt oriented
Best-fit (EPOBF)) that uses performance-per-watt as a metric to choose
which most energy-ecient PM for mapping each VM (e.g. the maxi-
mum of MIPS/Watt). Using information from Feitelsons Parallel Work-
load Archive to model HPC jobs, we compare the proposed EPOBF to
state-of-the-art heuristics on heterogeneous PMs (each PM has multicore
CPUs). Simulations show that the proposed EPOBF can significantly
reduce total energy consumption when compared with state-of-the-art
allocation heuristics.

· ·

Keywords: Cloud computing VM allocation Energy eciency

1 Introduction

Cloud computing has been developed as a utility computing model [ 8 ]andis
driven by economies of scale. High Performance Computing (HPC) clouds have
been popularly adopted [ 15 , 18 , 20 , 23 ] and are provided by industrial companies
such as Amazon Web Service Cloud [ 1 ]. A HPC cloud is a cloud system that
uses virtualization technology for provision of computational resources in form
of virtual machines (VMs) to run their HPC applications [ 11 , 18 ]. These cloud
systems are often built from virtualized data centers [ 5 , 22 ]. Powering these cloud
c