In ternational Journal of Computer Science Trends and Technology IJCST) Volume 4 Issue 2, Mar - Apr 2016 ISSN: 2347-8578www.ijcstjournal.org Page 157 EDHS Schedulability An alysis for Real-Time Multiprocessor Scheduling Rula Mreisheh [1] ,Mohammed Hijazieh [2] PhD Student [1] Department of Computer and Automatic Control Engineering Assistant P rofessor [2] Department of Computer and Automatic Control Engineering Tishreen University Lattakia-Syria ABSTRACT Scheduling algorithms play a main role in the design of real-time systems. Due to high processing and low price of m u lti process or s, real-time scheduling in s uch s ystem s is m ore m otivating but m ore co mplicated.E a rliest Deadli ne and Hi ghes t- priority Sp li t (EDHS ) is a s ched uling algori thm for s poradic tasks perform s similar to the t radi tional partitioningscheduling, as long as tasks are successfully partitioned, but if a spare capacity of each individual processor is not enough to accept the full execution of the task, then a task is allowed to be shared between multiple processors, beyond partitioning. In this paper, we m easure the EDHS nu mber of migrations for sporadic tasks under different utiliz ation bound s . We also co m pare the nu m ber of contex t switches, average deadline mi ss e s an d tasks average wai ting t ime of EDHS algorith m with we ll-k nown algorithms s uch as Partition Earliest Deadline First (P-EDF) and Partition Rate Monotonic (P-RM). In this comparison, the number of process ors and tasks has been increase d to evalua te the effect of this increment on the performance of the afore m ent ioned sched uli ng algori thms . Keywo r ds: -Multiprocessor System, Real Time Scheduling , EDHS algorithm, Sporadic tasks.I. INTRODUCTION The recent and rapid growth of real-time applications increases the use of computers to control safety critical real- time functions over the past few years. As a result, real-time systems [1] where the correctness of the system behaviour depends o n both the logical r esu lts of the computation and the time at which these results are produced, have become the focus of much study. Multiprocessor scheduling techniques fall into two general categories [1,2]: Global and Partitioning scheduling algorithms. In the global scheduling scheme, all ready tasks are kept in a global queue which is shared among all process ors. In the parti tioning s cheduling sc heme, the tasks are statically partitioned and all tasks in a partition are assigned to the same processorand always executed on it. Tasks are not allowed to mi grate, th eref ore th e mul t ipr oces sor scheduling problem is transformed to many uniprocessor scheduli ng proble m s . Recent studies hav e m ade a new class of multiprocessor scheduling, so-called semi-partitioning [3]. In semi-partitioning scheduling, most of tasks are assigned to particular proces so rs, but the rest of tas k s are allowed to mi grate between p rocessors. As a resul t, i t us uall y p erf orms bett er tha n partitioning, wh il e the number of migrati ons is m uch small er than global s ched uling [3] . Earliest Deadline and Highest-priority Split (EDHS) is a semi-partitioning scheduling algorithm presented by Kato & al. which improves schedulable multiprocessor utilization by 10 to 30 % over the tradi t ional partitioni ng app roach when i t sch edules s poradic tasks [4] . For EDHS [4,5], a traditional partitioning is performed before sp li tting the worst-case ex ecut ion t ime ( ei ) of a task. If the pa rtiti on ed s ched uling fail s, the rem ainingei portions are Shared on two or more processors. Each part of the task is defined in order to fill a processor. Kato & al. chose to assign at most one migrating task to each processor. A task always mi grates in th e same way, between the same processors an d at the same time of their execution. Here, the notion of semi- partitioned s che duling takes its full meaning. The reminder of this paper is organized as follows: In section II, we summarize the scheduling criteria we have considered i n th is paper. In sect ion I II, we introduce previous wor ks that s tudy and ev aluate r eal time scheduli ng algor ithms. In section IV, we describe our system model that we have carried out to evaluate scheduling algorithms. We analyze the performance of the E DHS algorith m d epen ding on diff erent values of parameters and we compare it with well-known algorithms such as Partition Earliest Deadline First (P-EDF) and Par titi on Rate Mo noto nic (P-R M) in section V. Finally, a conclusion is p resented in section V I. RESE ARCH ARTICLE OPEN ACCESS
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
8/18/2019 [IJCST-V4I2P28]:Rula Mreisheh, Mohammed Hijazieh