TY - JOUR
T1 - Characterizing resource availability in enterprise desktop grids
AU - Kondo, Derrick
AU - Fedak, Gilles
AU - Cappello, Franck
AU - Chien, Andrew A.
AU - Casanova, Henri
N1 - Funding Information:
We gratefully acknowledge Kyung Ryu and Amin Vahdat for providing the UCB trace data set and documentation. This material is based upon work supported by the National Science Foundation under Grant ACI-0305390.
PY - 2007/8
Y1 - 2007/8
N2 - Desktop grids, which use the idle cycles of many desktop PCs, are one of the largest distributed systems in the world. Despite the popularity and success of many desktop grid projects, the heterogeneity and volatility of hosts within desktop grids have been poorly understood. Yet, resource characterization is essential for accurate simulation and modelling of such platforms. In this paper, we present application-level traces of four real desktop grids that can be used for simulation and modelling purposes. In addition, we describe aggregate and per host statistics that reflect the heterogeneity and volatility of desktop grid resources. Finally, we apply our characterization to develop a performance model for desktop grid applications for various task granularities, and then use a cluster equivalence metric to quantify the utility of the desktop grid relative to that of a dedicated cluster for task-parallel applications.
AB - Desktop grids, which use the idle cycles of many desktop PCs, are one of the largest distributed systems in the world. Despite the popularity and success of many desktop grid projects, the heterogeneity and volatility of hosts within desktop grids have been poorly understood. Yet, resource characterization is essential for accurate simulation and modelling of such platforms. In this paper, we present application-level traces of four real desktop grids that can be used for simulation and modelling purposes. In addition, we describe aggregate and per host statistics that reflect the heterogeneity and volatility of desktop grid resources. Finally, we apply our characterization to develop a performance model for desktop grid applications for various task granularities, and then use a cluster equivalence metric to quantify the utility of the desktop grid relative to that of a dedicated cluster for task-parallel applications.
KW - Cycle stealing
KW - Desktop grids
KW - Resource availability
KW - Resource characterization
UR - http://www.scopus.com/inward/record.url?scp=34248551294&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34248551294&partnerID=8YFLogxK
U2 - 10.1016/j.future.2006.11.001
DO - 10.1016/j.future.2006.11.001
M3 - Article
AN - SCOPUS:34248551294
SN - 0167-739X
VL - 23
SP - 888
EP - 903
JO - Future Generation Computer Systems
JF - Future Generation Computer Systems
IS - 7
ER -