TY - JOUR
T1 - Online parallel scheduling of non-uniform tasks
T2 - Trading failures for energy
AU - Fernández Anta, Antonio
AU - Georgiou, Chryssis
AU - Kowalski, Dariusz R.
AU - Zavou, Elli
N1 - Funding Information:
This research was supported in part by the Comunidad de Madrid grant Cloud4BigData-CM ( S2013/ICE-2894 ), Spanish MICINN / MINECO grant TEC2011-29688-C02-01 , NSF of China grant 61020106002 , and FPU12/00505 Grant from MECD . A preliminary version of this work appears in the proceedings of FCT 2013.
Publisher Copyright:
© 2015 Elsevier B.V.
PY - 2015/7/26
Y1 - 2015/7/26
N2 - Consider a system in which tasks of different execution times arrive continuously and have to be executed by a set of machines that are prone to crashes and restarts. In this paper we model and study the impact of parallelism and failures on the competitiveness of such an online system. In a fault-free environment, a simple Longest-In-System scheduling policy, enhanced by a redundancy-avoidance mechanism, guarantees optimality in a long-term execution. In the presence of failures though, scheduling becomes a much more challenging task. In particular, no parallel deterministic algorithm can be competitive against an off-line optimal solution, even with one single machine and tasks of only two different execution times. We find that when additional energy is provided to the system in the form of processing speedup, the situation changes. Specifically, we identify thresholds on the speedup under which such competitiveness cannot be achieved by any deterministic algorithm, and above which competitive algorithms exist. Finally, we propose algorithms that achieve small bounded competitive ratios when the speedup is over the threshold.
AB - Consider a system in which tasks of different execution times arrive continuously and have to be executed by a set of machines that are prone to crashes and restarts. In this paper we model and study the impact of parallelism and failures on the competitiveness of such an online system. In a fault-free environment, a simple Longest-In-System scheduling policy, enhanced by a redundancy-avoidance mechanism, guarantees optimality in a long-term execution. In the presence of failures though, scheduling becomes a much more challenging task. In particular, no parallel deterministic algorithm can be competitive against an off-line optimal solution, even with one single machine and tasks of only two different execution times. We find that when additional energy is provided to the system in the form of processing speedup, the situation changes. Specifically, we identify thresholds on the speedup under which such competitiveness cannot be achieved by any deterministic algorithm, and above which competitive algorithms exist. Finally, we propose algorithms that achieve small bounded competitive ratios when the speedup is over the threshold.
KW - Competitiveness
KW - Energy efficiency
KW - Failures
KW - Non-uniform tasks
KW - Online algorithms
KW - Scheduling
UR - http://www.scopus.com/inward/record.url?scp=84944887867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84944887867&partnerID=8YFLogxK
U2 - 10.1016/j.tcs.2015.01.027
DO - 10.1016/j.tcs.2015.01.027
M3 - Article
AN - SCOPUS:84944887867
SN - 0304-3975
VL - 590
SP - 129
EP - 146
JO - Theoretical Computer Science
JF - Theoretical Computer Science
ER -