Information Technology Reference
In-Depth Information
Implications of CPU Dynamic Performance
and Energy-Efficient Technologies on the Intrusiveness
Generated by Desktop Grids Based on Virtualization
Germán Sotelo, Eduardo Rosales, and Harold Castro
Universidad de los Andes, Systems and Computing Engineering Department,
School of Engineering, Colombia
{ga.sotelo69,ee.rosales24,hcastro}@uniandes.edu.co
Abstract. We evaluate how dynamic performance and energy-efficient
technologies, as features introduced in modern processor architectures, affect
the intrusiveness that Desktop Grids based on virtualization generate on desk-
tops. Such intrusiveness is defined as degradation in the performance perceived
by an end-user that is using a desktop while it is opportunistically utilized by
Desktop Grid systems. To achieve this, we deploy virtual machines on a selec-
tion of desktops representing recent processor architectures. We then bench-
mark CPU intensive workloads simultaneously executed on both the virtual and
the physical environment. The results show that dynamic performance and
energy-efficient technologies, when incorporated on the supporting desktops,
directly affect the level of intrusiveness an end-user perceives. Furthermore,
depending on the processor architecture the intrusiveness percentage varies in a
range from 3% to 100%. Finally, we propose policies aimed to minimize such
intrusiveness according to the supporting processor architectures to be utilized
and end-user profiles.
Keywords: Desktop Grid, Grid Computing, Volunteer Computing, Benchmark-
ing, Virtualization, Intrusiveness, Performance.
1 Introduction
Desktop Grid Computing benefits from idle computing resources available in volun-
teer computers around the world (known as Public, Global, Peer-to-Peer, Public-
Resource, or Internet-based Desktop Grids) or desktops deployed at an institution
(known as Local, Private, or Enterprise Desktop Grids) [13]. These efforts mostly aim
to support e-Science projects by integrating non-dedicated, distributed, and heteroge-
neous computing resources that usually belong to different administrative domains in
order to provide large-scale computational capacities at low-cost. Since desktops tend
to be underutilized during significant periods, there is usually a large amount of idle
computing resources available (processing, networking and storage). Therefore, Desk-
top Grids are an economically attractive solution to deploy large-scale computing
infrastructures, avoiding not only underutilization, but also financial investments in
new and dedicated hardware.
 
Search WWH ::




Custom Search