The impact of task service time variability on gang scheduling performance in a two-cluster system

Abstract Gang scheduling is a common task scheduling policy for parallel and distributed systems which combines elements of space-sharing and time-sharing. In this paper we present a migration strategy which reduces the fragmentation in the schedule caused by gang scheduled jobs. We consider the existence of high priority jobs in the workload. These jobs need to be started immediately and they may interrupt a parallel job’s execution. A distributed system consisting of two homogeneous clusters is simulated to evaluate the performance for various workloads. We study the impact on performance of the variability in service time of the parallel tasks. Our simulation results indicate that the proposed strategy can result in a significant performance gain and that the performance improvement depends on the variability of gang tasks’ service time.

[1]  Phil Andrews,et al.  Impact of Reservations on Production Job Scheduling , 2007, JSSPP.

[2]  H. Karatza.  SCHEDULING GANGS IN A DISTRIBUTED SYSTEM , 2006 .

[3]  Laxmikant V. Kalé,et al.  Proactive Fault Tolerance in MPI Applications Via Task Migration , 2006, HiPC.

[4]  Dror G. Feitelson,et al.  Improved Utilization and Responsiveness with Gang Scheduling , 1997, JSSPP.

[5]  Anand Sivasubramaniam,et al.  An Integrated Approach to Parallel Scheduling Using Gang-Scheduling, Backfilling, and Migration , 2001, IEEE Trans. Parallel Distributed Syst..

[6]  Bharadwaj Veeravalli,et al.  Design and performance evaluation of combined first-fit task allocation and migration strategies in mesh multiprocessor systems , 2008, Parallel Comput..

[7]  Mladen A. Vouk,et al.  Cloud Computing – Issues, Research and Implementations , 2008, CIT 2008.

[8]  Hassan Rajaei,et al.  Simulation of Job Scheduling for Small Scale Clusters , 2006, Proceedings of the 2006 Winter Simulation Conference.

[9]  Dejan S. Milojicic,et al.  Process migration , 1999, ACM Comput. Surv..

[10]  Doug Johnson,et al.  Computing in the Clouds. , 2010 .

[11]  Dror G. Feitelson,et al.  Paired Gang Scheduling , 2003, IEEE Trans. Parallel Distributed Syst..

[12]  Gunter Bolch,et al.  Queueing Networks and Markov Chains , 2005 .

[13]  Helen D. Karatza,et al.  Performance evaluation of gang scheduling in a two-cluster system with migrations , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[14]  Cong Du,et al.  Dynamic Scheduling with Process Migration , 2007, Seventh IEEE International Symposium on Cluster Computing and the Grid (CCGrid '07).

[15]  Evgenia Smirni,et al.  Multiple-Queue Backfilling Scheduling with Priorities and Reservations for Parallel Systems , 2002, JSSPP.

[16]  Liu Zheng,et al.  A Task Migration Constrained Energy-Efficient Scheduling Algorithm for Multiprocessor Real-time Systems , 2007, 2007 International Conference on Wireless Communications, Networking and Mobile Computing.

[17]  Anand Sivasubramaniam,et al.  The Impact of Migration on Parallel Job Scheduling for Distributed Systems , 2000, Euro-Par.

[18]  Xiaoying Wang,et al.  Multi-cluster Load Balancing Based on Process Migration , 2007, APPT.

[19]  Helen D. Karatza.  Scheduling in Distributed Systems , 2003, MASCOTS Tutorials.

[20]  Helen D. Karatza.  Gang scheduling in a distributed system under processor failures and time-varying gang size , 2003, The Ninth IEEE Workshop on Future Trends of Distributed Computing Systems, 2003. FTDCS 2003. Proceedings..

[21]  Albert Y. Zomaya,et al.  Efficient clustering for parallel tasks execution in distributed systems , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[22]  Angela C. Sodan,et al.  Gang scheduling and adaptive resource allocation to mitigate advance reservation impact , 2006, Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06).

[23]  Helen D. Karatza,et al.  Performance of gang scheduling strategies in a parallel system , 2009, Simul. Model. Pract. Theory.

[24]  Sanjeev Setia.  Trace-driven analysis of migration-based gang scheduling policies for parallel computers , 1997, Proceedings of the 1997 International Conference on Parallel Processing (Cat. No.97TB100162).

[25]  Averill M. Law,et al.  Simulation modelling and analysis , 1991 .

[26]  Achim Streit.  Enhancements to the Decision Process of the Self-Tuning dynP Scheduler , 2004, JSSPP.

[27]  Dimiter R. Avresky,et al.  Method for Task Migration in Grid Environments , 2005, Fourth IEEE International Symposium on Network Computing and Applications.