Performance Analysis Of Concurrent Tasks Scheduling Schemes In A Heterogeneous Distributed Computing System

Abstract

Performance of distributed systems can be improved from scheduling of tasks aspect. A good scheduling algorithm can enhance the performance of the distributed system significantly. In this paper we have compared the performance of batch mode and immediate mode schedulers in heterogeneous distributed computing environment. An immediate mode scheduler only considers a single task for scheduling on a FCFS (first come, first served) basis while a batch mode scheduler considers a number of tasks at once for scheduling. In particular we have used two immediate mode scheduler: (i) the earliest first (EF) algorithm and (ii) the lightest loaded (LL), and two batch mode heuristic scheduler (i) the max-min (MX) scheduler and (ii) min-min (MM) scheduler. The main aim of max-min (MX) scheduler is to have the largest tasks scheduled as early as possible, with smaller tasks at the end filling in the gaps. The min-min (MM) scheduler is similar to the MX scheduler, except tasks are sorted in ascending order according to size. We have simulated the scheduler behavior with our simulator developed using Matlab, where each task is with the expected execution time and expected completion time on a particular machine. This findings are used to design an adaptive dynamic scheduler that selects the best strategy depending on load at a particular time frame. The results are also useful in deciding the effective group size of a processor pool (cluster) for the HDCS, which can be remodeled as a tree of resource clusters that are geographically distributed. We have also outline the proposed scheduler framework that uses (i) a global scheduler, responsible for determining where to send task submitted to it, a local scheduler, responsible for determining the order in which tasks are executed at that particular processor pool.