Search

Real-time systems are computing systems that must react within precise time constraints to events in the environment. As a consequence, the correct behavior of these systems depends not only on the value of the computation but also on the time at which the results are produced [SR88]. A reaction that occurs too late could be useless or even dangerous. Today, real-time computing plays a crucial role in our society, since an increasing number of complex systems rely, in part or completely, on computer control. Examples of applications that require real-time computing include [ABSTRACT FROM AUTHOR]

Current operating systems having real-time characteristics can be divided into three main categories: 1.Priority-based kernel for embedded applications,2.Real-time extensions of timesharing operating systems, and3.Research operating systems. [ABSTRACT FROM AUTHOR]

In this chapter we discuss some important issues related to the design and the development of complex real-time applications requiring sensory acquisition, control, and actuation of mechanical components. The aim of this part is to give a precise characterization of control applications, so that theory developed for real-time computing and scheduling algorithms can be practically used in this field to make complex control systems more reliable. In fact, a precise observation of the timing constraints specified in the control loops and in the sensory acquisition processes is a necessary condition for guaranteeing a stable behavior of the controlled system, as well as a predictable performance. [ABSTRACT FROM AUTHOR]

In this chapter we present some basic issues that should be considered during the design and the development of a hard real-time kernel for critical control applications. For didactical purposes, we illustrate the structure and the main components of a small real-time kernel, called DICK (DIdactic C Kernel), mostly written in C language, which is able to handle periodic and aperiodic tasks with explicit time constraints. The problem of time predictable intertask communication is also discussed, and a particular communication mechanism for exchanging state messages among periodic tasks is illustrated. Finally, we show how the runtime overhead of the kernel can be evaluated and taken into account in the schedulability analysis. [ABSTRACT FROM AUTHOR]

This chapter deals with the problem of scheduling real-time tasks in overload conditions; that is, in those critical situations in which the computational demand requested by the task set exceeds the time available on the processor, and hence not all tasks can complete within their deadlines. [ABSTRACT FROM AUTHOR]

A resource is any software structure that can be used by a process to advance its execution. Typically, a resource can be a data structure, a set of variables, a main memory area, a file, or a set of registers of a peripheral device. A resource dedicated to a particular process is said to be private, whereas a resource that can be used by more tasks is called a shared resource. A shared resource protected against concurrent accesses is called an exclusive resource. [ABSTRACT FROM AUTHOR]

In this chapter1 we discuss the problem of scheduling soft aperiodic tasks and hard periodic tasks under dynamic priority assignments. In particular, different service methods are introduced, whose objective is to reduce the average response time of aperiodic requests without compromising the schedulability of hard periodic tasks. Periodic tasks are scheduled by the Earliest Deadline First (EDF) algorithm. [ABSTRACT FROM AUTHOR]

The scheduling algorithms treated in the previous chapters deal with homogeneous sets of tasks, where all computational activities are either aperiodic or periodic. Many real-time control applications, however, require both types of processes, which may also differ for their criticalness. Typically, periodic tasks are time-driven and execute critical control activities with hard timing constraints aimed at guaranteeing regular activation rates. Aperiodic tasks are usually event-driven and may have hard, soft, or non-real-time requirements depending on the specific application. [ABSTRACT FROM AUTHOR]

In many real-time control applications, periodic activities represent the major computational demand in the system. Periodic tasks typically arise from sensory data acquisition, low-level servoing, control loops, action planning, and system monitoring. Such activities need to be cyclically executed at specific rates, which can be derived from the application requirements. Some specific examples of real-time applications are illustrated in Chapter 10. [ABSTRACT FROM AUTHOR]

In this chapter we present a variety of algorithms for scheduling real-time aperiodic tasks on a single machine environment. Each algorithm represents a solution for a particular scheduling problem, which is expressed through a set of assumptions on the task set and by an optimality criterion to be used on the schedule. The restrictions made on the task set are aimed at simplifying the algorithm in terms of time complexity. When no restrictions are applied on the application tasks, the complexity can be reduced by employing heuristic approaches, which do not guarantee to find the optimal solution to a problem but can still guarantee a feasible schedule in a wide range of situations. [ABSTRACT FROM AUTHOR]

Over the last few years, several algorithms and methodologies have been proposed in the literature to improve the predictability of real-time systems. In order to present these results we need to define some basic concepts that will be used throughout the book. We begin with the most important software entity treated by any operating system, the process. A process is a computation that is executed by the CPU in a sequential fashion. In this text, the terms process and task are used as synonyms. However, it is worth saying that some authors prefer to distinguish them and define a task as a sequential execution of code that does not suspend itself during execution, whereas a process is a more complex computational activity, that can be composed by many tasks. [ABSTRACT FROM AUTHOR]

In this chapter we discuss some important issues related to the design and the development of complex real-time applications requiring sensory acquisition, control, and actuation of mechanical components. The aim of this part is to give a precise characterization of control applications, so that theory developed for real-time computing and scheduling algorithms can be practically used in this field to make complex control systems more reliable. In fact, a precise observation of the timing constraints specified in the control loops and in the sensory acquisition processes is a necessary condition for guaranteeing a stable behavior of the controlled system, as well as a predictable performance. [ABSTRACT FROM AUTHOR]

Current operating systems having real-time characteristics can be divided into three main categories: 1.Priority-based kernel for embedded applications,2.Real-time extensions of timesharing operating systems, and3.Research operating systems. [ABSTRACT FROM AUTHOR]

In this chapter we present some basic issues that should be considered during the design and the development of a hard real-time kernel for critical control applications. For didactical purposes, we illustrate the structure and the main components of a small real-time kernel, called DICK (DIdactic C Kernel), mostly written in C language, which is able to handle periodic and aperiodic tasks with explicit time constraints. The problem of time predictable intertask communication is also discussed, and a particular communication mechanism for exchanging state messages among periodic tasks is illustrated. Finally, we show how the runtime overhead of the kernel can be evaluated and taken into account in the schedulability analysis. [ABSTRACT FROM AUTHOR]

This chapter deals with the problem of scheduling real-time tasks in overload conditions; that is, in those critical situations in which the computational demand requested by the task set exceeds the time available on the processor, and hence not all tasks can complete within their deadlines. [ABSTRACT FROM AUTHOR]

A resource is any software structure that can be used by a process to advance its execution. Typically, a resource can be a data structure, a set of variables, a main memory area, a file, or a set of registers of a peripheral device. A resource dedicated to a particular process is said to be private, whereas a resource that can be used by more tasks is called a shared resource. A shared resource protected against concurrent accesses is called an exclusive resource. [ABSTRACT FROM AUTHOR]

In this chapter1 we discuss the problem of scheduling soft aperiodic tasks and hard periodic tasks under dynamic priority assignments. In particular, different service methods are introduced, whose objective is to reduce the average response time of aperiodic requests without compromising the schedulability of hard periodic tasks. Periodic tasks are scheduled by the Earliest Deadline First (EDF) algorithm. [ABSTRACT FROM AUTHOR]

The scheduling algorithms treated in the previous chapters deal with homogeneous sets of tasks, where all computational activities are either aperiodic or periodic. Many real-time control applications, however, require both types of processes, which may also differ for their criticalness. Typically, periodic tasks are time-driven and execute critical control activities with hard timing constraints aimed at guaranteeing regular activation rates. Aperiodic tasks are usually event-driven and may have hard, soft, or non-real-time requirements depending on the specific application. [ABSTRACT FROM AUTHOR]

In this chapter we present a variety of algorithms for scheduling real-time aperiodic tasks on a single machine environment. Each algorithm represents a solution for a particular scheduling problem, which is expressed through a set of assumptions on the task set and by an optimality criterion to be used on the schedule. The restrictions made on the task set are aimed at simplifying the algorithm in terms of time complexity. When no restrictions are applied on the application tasks, the complexity can be reduced by employing heuristic approaches, which do not guarantee to find the optimal solution to a problem but can still guarantee a feasible schedule in a wide range of situations. [ABSTRACT FROM AUTHOR]

In many real-time control applications, periodic activities represent the major computational demand in the system. Periodic tasks typically arise from sensory data acquisition, low-level servoing, control loops, action planning, and system monitoring. Such activities need to be cyclically executed at specific rates, which can be derived from the application requirements. Some specific examples of real-time applications are illustrated in Chapter 10. [ABSTRACT FROM AUTHOR]

Over the last few years, several algorithms and methodologies have been proposed in the literature to improve the predictability of real-time systems. In order to present these results we need to define some basic concepts that will be used throughout the book. We begin with the most important software entity treated by any operating system, the process. A process is a computation that is executed by the CPU in a sequential fashion. In this text, the terms process and task are used as synonyms. However, it is worth saying that some authors prefer to distinguish them and define a task as a sequential execution of code that does not suspend itself during execution, whereas a process is a more complex computational activity, that can be composed by many tasks. [ABSTRACT FROM AUTHOR]

Real-time systems are computing systems that must react within precise time constraints to events in the environment. As a consequence, the correct behavior of these systems depends not only on the value of the computation but also on the time at which the results are produced [SR88]. A reaction that occurs too late could be useless or even dangerous. Today, real-time computing plays a crucial role in our society, since an increasing number of complex systems rely, in part or completely, on computer control. Examples of applications that require real-time computing include [ABSTRACT FROM AUTHOR]