Enhanced Preemptive Global Utility Accrual Real Time Scheduling Algorithms in Multicore Environment

Idawaty Ahmad,Zuriati Ahmad Zulkarnain,Mohamed Othman

doi:10.3844/jcssp.2015.1099.1107

Abstract

This paper proposed an efficient real time scheduling algorithm using global scheduling paradigm running in multicore environment known as Global Preemptive Utility Accrual Scheduling (GPUAS) algorithm. The existing TUF/UA multiprocessor scheduling algorithms known as Greedy-Global Utility Accrual (G-GUA) and Non Greedy-Global Utility Accrual (NG-GUA) algorithms is seen to overlook the efficiency on its task scheduling algorithm. These algorithms have adapted the task migration attribute considering the load balancing problem in multi core platform. The existing PUAS uniprocessor scheduling algorithm is mapped into the multicore scheduling environment that consists of the global scheduling schemes considering the migration attribute of the executed tasks. The main principal of global scheduling is that it allows the executed tasks to migrate from one processor to the other processors whenever a scheduling event occurs in the system. The proposed GPUAS algorithm inherits the characteristics of PUAS in uniprocessor where it can preempt the highest PUD task at any event that occurs in the system. In this research, the proposed GPUAS algorithm enhanced the existing NG-GUA and G-GUA algorithms. The developed simulator has derived the set of parameter, events and performance metrics according to a detailed analysis of the base model. The proposed GPUAS algorithm achieved the highest accrued utility for the entire load range. The proposed GPUAS algorithm is more efficient than the existing algorithms, producing the highest accrued utility ratio and less abortion ratio making it more suitable and efficient for real time application domain.

Highlights

In the presence of extremely overloaded tasks traffic, the RTS requires multicore environment with an efficient load sharing capability to accommodate the surplus load
The proposed Global Preemptive Utility Accrual Scheduling (GPUAS) algorithm is compared with the existing Non Greedy-Global Utility Accrual (NG-GUA) and Greedy-Global Utility Accrual (G-GUA) algorithms
Simulation results revealed that GPUAS2 has improved for less than 4.98% on G-GUA in dual core platform and remain the same performances in quad and eight core platforms

Summary

Introduction

In the presence of extremely overloaded tasks traffic, the RTS requires multicore environment with an efficient load sharing capability to accommodate the surplus load. G-GUA uses a greedy strategy where task whose execution yields the maximum PUD is selected to be scheduled at a particular instance. The requesting task is placed at the queue that has the least remaining execution cost This requesting task assignment behavior in G-GUA may affect the total utility accrued because it does not consider the value of utility when determining the suitable queue at that particular instance. NG-GUA uses dual metric to overcome overloaded tasks in RTS If the underlying scheduling scheme can reduce the abortion of the requesting task efficiently, the system will possibly attain a higher utility enhancing the overall system’s performance

Methods

Results

Discussion

Conclusion