Hybrid online/offline scheduling for hard real-time systems

Real-Time Systems Symposium, …, 1999

1999

This paper proposes e cient scheduling algorithms for the joint scheduling of hard aperiodic, sporadic and periodic real time tasks, in systems based on preemptive, xed-priority dispatching. Our scheme guarantees or rejects hard aperiodic real time tasks without any prior knowledge of their attributes, by managing the idle processor capacity dynamically. The method assigns xed priorities to periodic tasks based on the Deadline Monotonic (DM) scheme and analyzes their schedule o -line. We derive closed form solutions for the idle processor capacity process Z(t) within a schedule. In the absence of pending dynamic tasks, periodic tasks execute in their earliest possible schedule S F , called the Fixed-Priority First (FPF). Upon the arrival of a non-periodic task Ja, the scheduler directly determines its admissibility, based on closed form equation of the available processor time in the current schedule, until the deadline of Ja. If Ja cannot be guaranteed under FPF, the scheduler evaluates the idle processor capacity of an alternative schedule S L , where periodic tasks are delayed to execute at their latest possible times, called the Latest Deadline Last (LDL). If LDL o ers su cient idle capacity, the scheduler switches all periodic tasks from FPF to LDL, assigns Ja the lowest priority and admits it into the system. Otherwise, it immediately rejects Ja. We develop the theoretical framework and derive e cient algorithms to compute the idle processors capacity Z(a; b) within a time interval a; b], and maintain it when the schedule is adjusted. The algorithms can also reclaim unused capacity from guaranteed tasks. Our admission control procedure has computational complexity (n) when the non-periodic task queue is serviced in FIFO order, with n periodic tasks. Previously proposed methods have pseudopolynomial time and space complexity. Experimental results show that with n = 160 periodic tasks, the actual computation time for the admission control procedure is less than 90 -secs on a SUN Ultra-Sparc I, 143MHz machine and less than 30 -secs on a SGI Origin 2000, 250MHz workstation. Experiments on well known task sets show overheads which are below 10 -secs even for the slowest machine. The proposed methodology easily extends to algorithms that minimize total task tardiness and number of tardy tasks.

Information Processing Letters, 2006

International Journal of Computer Applications, 2015

In this paper, main scheduling algorithms for hard real-time systems (RTSs) have been investigated that include both uni and multi processors schemes. It provides the summary of schedulability analysis and well-known attributes. This paper composed of two parts; first part surveyed the basic hard RTS scheduling algorithms that guarantee the on-time completion of the tasks. Second part contains the different heuristic and partitioned approaches for some specific factors of real-time systems such as energy consumption, dependability, performance, scheduling feasibility and utilization of memory resource. Finally, the analysis and evaluation of the mentioned methods are shown based on the schedulability of task sets and efficiency.

ukpmc.ac.uk

2008

When dealing with soft real-time tasks with highly variable execution times in open systems, an approach that is becoming popular is to use feedback scheduling techniques to dynamically adapt the bandwidth reserved to each task. According to this model, each task is assigned an adaptive reservation, with a variable budget and a constant period. The response times of the jobs of the task are monitored and if different from expected (i.e. much larger or much shorter than the task relative deadline), a feedback control law adjusts the reservation budget accordingly. However, when the feedback law algorithm demands an increase of the reservation budget, the system must run a schedulability test to check if there is enough spare bandwidth to accommodate such increase. The schedulability test must be very efficient, as it may be performed at each budget update, i.e. potentially at each instance of a task.

2001

2006

Solving a scheduling problem consists in finding an initial solution able to model all the complex constraints that relate the problem activities. Moreover, the solving process should be necessarily considered as propaedeutic for the next phase of any schedule's life: its execution in the real world. The inherent unpredictability of real working environments poses serious difficulties to which the scheduling community normally responds by (1) introducing methodologies that tend to increase schedule robustness (off-line phase, proactive approach), and by developing fast-reaction techniques to be employed during schedule execution (on-line phase, reactive approach).

2000

We propose a model oriented scheduling methodology for highly coupled real time applications. We show that variations in the computation times of tasks may hazard the safeness of the controlled process. For the sake of reliability we take conditional instructions of tasks' code explicitly into account, in order to reduce the potential failures. We fisrt adapt the task's temporal model

2008 Euromicro Conference on Real-Time Systems, 2008

Task period adaptations are often used to alleviate temporal overload conditions in real-time systems. Existing frameworks assume that only task periods are adjustable and that task deadlines remain unchanged at all times. This paper formally introduces a more general real-time task model where task deadlines, which are less than or equal to task periods, are functions of task periods. This tight coupling between task deadlines and task periods has been discussed in a recent work in control systems and presents a novel real-time scheduling challenge. To solve the period and deadline selection problem, this article identifies a feasible period-deadline combination and proposes a heuristic, which iteratively adjusts task periods and deadlines in such a way that the task set becomes schedulable. Experimental results show that the heuristic finds a solution to the period and deadline selection problem over 73% of the time, using less than three search iterations. When it is unable to find a solution to the problem, the heuristic requires less than 0.02s to run in the worstcase (with at most 100 search iterations).

Proceedings. 2003 International Symposium on System-on-Chip (IEEE Cat. No.03EX748), 2003

Real-time systems are growing in complexity and realtime and soft real-time applications are becoming common in general-purpose computing environments. Thus, there is a growing need for scheduling solutions that simultaneously support processes with a variety of different timeliness constraints. Toward this goal we have developed the Resource Allocation/Dispatching (RAD) integrated scheduling model and the Rate-Based Earliest Deadline (RBED) integrated multi-class real-time scheduler based on this model. We present RAD and the RBED scheduler and formally prove the correctness of the operations that RBED employs. We then describe our implementation of RBED and present results demonstrating how RBED simultaneously and seamlessly supports hard real-time, soft real-time, and best-effort processes.

2004

This report addresses the problem of scheduling for real-time systems that include both hard and soft tasks. In order to capture the relative importance of soft tasks and how the quality of results is affected when missing a soft deadline, we use utility functions associated to soft tasks. Thus the aim is to find the execution order of tasks that makes the total utility maximum and guarantees hard deadlines. We consider intervals rather than fixed execution times for tasks. Since a purely off-line solution is too pessimistic and a purely on-line approach incurs an unacceptable overhead due to the high complexity of the problem, we propose a quasi-static approach where a number of schedules are prepared at design-time and the decision of which of them to follow is taken at run-time based on the actual execution times. We propose an exact algorithm as well as different heuristics for the problem addressed in this report.

Asian Journal of Control, 2008

A scheduling technique is presented to minimize service delay of aperiodic tasks in hard real-time systems that employ dynamic-priority scheduling and do not allow task preemption. In a real-time scheduling process, the execution of periodic tasks can be deferred as long as this does not cause other tasks to violate their time constraints. However, aperiodic tasks that usually have urgent missions should complete execution as early as possible. In this paper, it is assumed that aperiodic tasks also have time constraints. Thus, the problem of deciding whether an aperiodic task with an unpredictable arrival time can be scheduled successfully or not is difficult to solve because delaying periodic tasks may cause them to fail to meet their time constraints. We present a dynamic scheduling technique to solve this problem which makes use of the symmetric property of a schedule. The maximum possible idle slot is always reserved at every scheduling point so that aperiodic tasks can be serviced immediately if the reserved idle slot is big enough to service them. The proposed technique also maximizes utilization of idle slots by reserving them for the longest possible time span.

Journal of Systems and Software

This paper presents the Clearing Fund Protocol, a three layered protocol designed to schedule soft real-time sets of precedence related tasks with shared resources. These sets are processed in an open dynamic environment. Open because new applications may enter the system ...

International …, 2011

Abstract: For real-time applications, task scheduling is a problem of paramount importance. Several scheduling algorithms were proposed in the literature, starting from static scheduling or cyclic executives which provide very deterministic yet inflexible behaviour, ...