Conference Paper

Realtss: a real-time scheduling simulator

Inst. Tecnologico de Mexicali, Mexicali
DOI: 10.1109/ICEEE.2007.4344998 Conference: Electrical and Electronics Engineering, 2007. ICEEE 2007. 4th International Conference on
Source: IEEE Xplore

ABSTRACT Real-time scheduling theory has shown an impressive evolution in the past few years. As a consequence of the intensive research done in this area a lot of new scheduling policies had been proposed to date. Nevertheless, just a few of such scheduling policies are available in existing real-time operating systems (RTOS). In this paper, we describe Realtss, an open source realtime scheduling simulator which is suited to simulate real-time scheduling algorithms without the need of implement them in a RTOS. Realtss is an invaluable teaching and researching tool since existing and new real-time scheduling policies can be easily evaluated.

1 Bookmark
  • [Show abstract] [Hide abstract]
    ABSTRACT: Increasing Deadline Meeting Rate (DMTR) during overload is a concern of Soft Real Time (SRT) Scheduling. Here we present our non-preemptive non-resource constraint scheduling model implemented on an open source discrete event simulator named OmNET. The model is simple, yet it fulfill the simulation purpose, which mimics execution of jobs schedule under non-preemptive and non-resource constraint system within usual real time timing parameters namely release time, execution time, deadline and period. We show that OmNET is capable to be used as a real time scheduling simulator. Along with, we also present the approach we undertook to design our novel SRT scheduling algorithm. The simulation result presented here shows the effect of Deadline Tolerance (SRT parameter) and Deadline size on DMTR. We conclude that our algorithm named gutEDF could produce higher DMTR as compared to Earliest Deadline First (EDF) algorithm during overload while maintaining optimum performance under normal load.
    Computational Intelligence, Modelling and Simulation (CIMSiM), 2012 Fourth International Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Real-time systems have relied on multiprocessor architectures since some time ago. However, the proliferation of multi-core architectures, which have multiple processing units on a single chip, has increased the interest on such systems. As a consequence, scheduling techniques for multiprocessor architectures have received considerable attention in recent years. In the last decade, a lot of scheduling algorithms have been proposed. In many cases, the least upper bound for these algorithms is about 50% of the whole system utilization, which is very pessimistic. One alternative to verify the schedulability of a real-time task set with a larger system utilization on a multiprocessor system, is through the use of exhaustive simulation. In this paper, we introduce RealtssMP, a tool to perform scheduling analysis and simulation of multiprocessor real-time scheduling algorithms. The proposed tool has shown to be helpful in the evaluation of the performance of existing and new scheduling algorithms. Moreover, it can be be used as an educational tool.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: There are several scheduling simulators to verify the behavior of real-time applications under different task scheduling algorithms. Current simulators cannot model the application accurately, and consequently the result of the simulation differs considerably from the actual behavior on a real computing system. This paper presents a scheduling simulator with application modeling capabilities for real-time applications. The proposed approach supports modeling of complex task control flows and dependency relations between tasks. In order to evaluate the modeling capabilities, we modeled a real engine control application and simulated it. We measured the response times of the application model running on our scheduling simulator and compared them with the ones obtained by running the real engine application binaries on an instruction set simulator. The average percentage errors in mean and worst-case response time between both simulations were only 9.6% and 8.6% respectively.


Available from