TY - GEN
T1 - Scheduling parallel tasks onto opportunistically available cloud resources
AU - He, Ting
AU - Chen, Shiyao
AU - Kim, Hyoil
AU - Tong, Lang
AU - Lee, Kang Won
PY - 2012/10/2
Y1 - 2012/10/2
N2 - We consider the problem of opportunistically scheduling low-priority tasks onto underutilized computation resources in the cloud left by high-priority tasks. To avoid conflicts with high-priority tasks, the scheduler must suspend the low-priority tasks (causing waiting), or move them to other underutilized servers (causing migration), if the high-priority tasks resume. The goal of opportunistic scheduling is to schedule the low-priority tasks onto intermittently available server resources while minimizing the combined cost of waiting and migration. Moreover, we aim to support multiple parallel low-priority tasks with synchronization constraints. Under the assumption that servers' availability to low-priority tasks can be modeled as ON/OFF Markov chains, we have shown that the optimal solution requires solving a Markov Decision Process (MDP) that has exponential complexity, and efficient solutions are known only in the case of homogeneously behaving servers. In this paper, we propose an efficient heuristic scheduling policy by formulating the problem as restless Multi-Armed Bandits (MAB) under relaxed synchronization. We prove the index ability of the problem and provide closed-form formulas to compute the indices. Our evaluation using real data center traces shows that the performance result closely matches the prediction by the Markov chain model, and the proposed index policy achieves consistently good performance under various server dynamics compared with the existing policies.
AB - We consider the problem of opportunistically scheduling low-priority tasks onto underutilized computation resources in the cloud left by high-priority tasks. To avoid conflicts with high-priority tasks, the scheduler must suspend the low-priority tasks (causing waiting), or move them to other underutilized servers (causing migration), if the high-priority tasks resume. The goal of opportunistic scheduling is to schedule the low-priority tasks onto intermittently available server resources while minimizing the combined cost of waiting and migration. Moreover, we aim to support multiple parallel low-priority tasks with synchronization constraints. Under the assumption that servers' availability to low-priority tasks can be modeled as ON/OFF Markov chains, we have shown that the optimal solution requires solving a Markov Decision Process (MDP) that has exponential complexity, and efficient solutions are known only in the case of homogeneously behaving servers. In this paper, we propose an efficient heuristic scheduling policy by formulating the problem as restless Multi-Armed Bandits (MAB) under relaxed synchronization. We prove the index ability of the problem and provide closed-form formulas to compute the indices. Our evaluation using real data center traces shows that the performance result closely matches the prediction by the Markov chain model, and the proposed index policy achieves consistently good performance under various server dynamics compared with the existing policies.
UR - http://www.scopus.com/inward/record.url?scp=84866771828&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866771828&partnerID=8YFLogxK
U2 - 10.1109/CLOUD.2012.15
DO - 10.1109/CLOUD.2012.15
M3 - Conference contribution
AN - SCOPUS:84866771828
SN - 9780769547558
T3 - Proceedings - 2012 IEEE 5th International Conference on Cloud Computing, CLOUD 2012
SP - 180
EP - 187
BT - Proceedings - 2012 IEEE 5th International Conference on Cloud Computing, CLOUD 2012
T2 - 2012 IEEE 5th International Conference on Cloud Computing, CLOUD 2012
Y2 - 24 June 2012 through 29 June 2012
ER -