90 likes | 222 Views
A Pareto Frontier for Optimizing Data Transfer vs. Job Execution in Grids. Javid Taheri | Postdoctoral Research Fellow. Albert Y. Zomaya | Professor and Director. Centre for Distributed and High Performance Computing School of Information Technologies
E N D
A Pareto Frontier for Optimizing Data Transfer vs. Job Execution in Grids Javid Taheri | Postdoctoral Research Fellow Albert Y. Zomaya| Professor and Director Centre for Distributed and High Performance Computing School of Information Technologies The University of Sydney, Sydney, Australia
Introduction to Grid Computing • Problem Statement: Data-Aware Job Scheduling • Preliminaries • Pareto Frontier • Genetic Algorithm (GA) • GA-ParFnt • Simulation and Analysis of Results • Conclusion
Problem Statement • Data Aware Job Scheduling (DAJS) • (1) the overall execution time of a batch of jobs (NP-Complete) • (2) transfer time of all datafiles to their dependent jobs(NP-Complete) Computation Nodes Storage Nodes File 1 Job 1 File 2 Job 2 File 3 Job 3 ... ... Job N File M
Problem Statement (cont.) SN CN Scheduler SN CN SN CN
Preliminaries • Pareto Front • Genetic Algorithm
Discussion and Analysis • GA-ParFnt’s Behavior and Performance • Scheduling Algorithms • Allocating jobs is much harder than replicating datafiles Test-Grid-8-4 Test-Grid-8-16 Test-Grid-8-8
THANK YOU Questions?