Schedulability Analysis of Task Sets with Upper- and Lower-Bound Temporal Constraints

As multiprocessor (or multicore) real-time systems become popular, there has been much research on multiprocessor real-time scheduling algorithms. This work evaluates EDZL (Earliest Deadline until Zero Laxity), a scheduling algorithm for real-time multiprocessor systems. First, we compare the performance of EDZL schedulability tests. We measure and compare the ratio of task sets admitted by each test. We also investigate the dominance between EDZL schedulability tests and discover that the union of the demand-based test and the utilization-based test is an effective combination. Second, we compare the schedulability of EDZL and EDF(k). We prove that the union of the EDZL schedulability tests dominates the EDF(k) schedulability test, i.e., the union of the EDZL schedulability tests can admit all task sets admitted by the EDF(k) schedulability test. We also compare the schedulability of EDZL and EDF(k) through scheduling simulation by measuring the ratio of successfully scheduled task sets. EDZL can successfully schedule 7.0% more task sets than EDF(k).

We address the problem of schedulability analysis for a set of sporadic real-time tasks scheduled by the Global Earliest Deadline First (G-EDF) policy on a multiprocessor platform. State-of-the-art tests for schedulability analysis of multiprocessor global scheduling are often incomparable. That is, a task set that is judged not schedulable by a test may be verified to be schedulable by another test, and vice versa. In this paper, we first develop a new schedulability test that integrates the limited carry-in technique and Response Time Analysis (RTA) procedure for Global EDF schedulability analysis. Then, we provide an over-approximate variant of this test with better run-time efficiency. Later, we extend these two tests to self-suspending tasks. All schedulability tests proposed in the paper have provable dominance over their state-of-the-art counterparts. Finally, we conduct extensive comparisons among different schedulability tests. Our new tests show significant improvements for schedulability analysis of Global EDF.

Real-time systems usually consist of a set of periodic and sporadic tasks. Periodic tasks can be divided into two classes: synchronous and asynchronous. The first type does not define the task first release, contrary to the second. Hence, synchronous periodic tasks are assumed to be released at the worst instant: the critical instant. The schedulability test is reduced to check a single execution of the task under analysis. The integration of sporadic tasks is also straightforward: they are treated as a periodic task with maximum arrival frequency. On the other hand, asynchronous periodic tasks require a test for each release in the hyper period and the integration of sporadic tasks is not trivial: the worst release instant is unknown a priori. However, they do not assume that the tasks are released at the worst instant.This paper presents a new schedulability analysis method based on the Response Time Analysis (RTA) to determine the worst response time of both asynchronous periodic and sporadic tasks, scheduled by a fixed-priority preemptive algorithm with general deadlines. It also presents another method that enables the introduction of a user configurable degree of pessimism, reducing the hyper period dependency.

Cyber-physical systems are realized as those systems where the computation, communication and physical processes interact with each other (e.g., robotic systems, automotives, etc). A large class of cyber-physical systems are associated with strict timeliness requirements. They are known as ‘real-time systems’ (e.g., smart grids, avionics, etc). Industrial control systems (ICS) are real-time systems that consist of several closed-loop controls. The main components of a control loop are — a physical plant, sensors, actuators and a controller. The sensors transmit the measurement data to the controller that generates appropriate control signals to actuate the physical plant. Large-scale wireless sensor actuator networks form the main communication framework among the network devices in ICS. Most of the communications between each of these devices are periodic real-time flows with hard deadlines. To ensure reliability, the communication in these systems are time-division multiple access (TDMA) based. Dedicated network resources (time-slots and frequencies) are allocated to these devices in advance and the communication schedule is pre-computed to satisfy the hard deadlines of the real-time flows. The same schedule is repeated over time which makes the schedule predictable in nature. However, a malicious attacker can exploit this predictable time-slots in the schedules to launch timing attacks. Since these applications are time-critical, timing attacks can completely undermine the system performance leading the system to an unsafe state. Schedule randomization is a popular defense mechanism to mitigate timing attacks. Although a few works exist in the literature that use schedule randomization as a countermeasure against timing attacks in real-time uniprocessor systems, none of them are applicable for real-time wireless networks. Schedule randomization as a countermeasure against timing attacks in real-time wireless networks remained largely unexplored. With this objective in focus, this thesis addresses some schedule randomization techniques to mitigate timing attacks in real-time wireless networks. Among the existing wireless network protocols that are in use, the WirelessHART is the most suitable and widely adopted protocol in ICS. A WirelessHART protocol supports centralized architecture, TDMA based communication, multiple channels, etc. All of these characteristics of a WirelessHART network facilitate reliable and predictable communication with real-time flow guarantees in ICS. However, the predictable communication exposes the system to timing attacks, such as selective jamming attacks. Selective jamming attacks are stealthy attacks, however, it can lead the system to an unstable state and can disrupt the safety of the system. As a countermeasure against such attack in WirelessHART network, we propose a centralized schedule randomization technique that randomizes the time-slots and channels in the schedule over every hyperperiod (least common multiple of the periods of the real-time flows) without violating the hard deadlines of the real-time flows, while still satisfying the feasibility constraints of a schedule in a WirelessHART network. The centralized technique generates the schedules offline and distributes the schedules online, hence, cannot support any change in topology in the network. Further, this technique has energy overheads in distributing the schedules to all the network devices at runtime. Hence, we propose a distributed online schedule randomization technique that can generate random feasible schedules at runtime in each network device without affecting the closed-loop control stability. To increase the extent of randomization of time-slots in the schedules, this online distributed technique adopts a period adaptation strategy that can adjust the transmission periods of the real-time flows at runtime depending on the stability of the closed-loop controls. To support an ever-growing number of devices and dense connectivity, the fifth generation (5G) cellular networks is expected to serve as the main communication standard in the future wireless sensor networks. Among the different service categories supported by 5G, the ultra-reliable low-latency communication (URLLC) is mostly suitable for time-critical applications such as the ICS. The communication in 5G is organized into slots over multiple frequencies. To satisfy the hard deadlines of the URLLC flows in ICS, a part of the resources (slots and frequencies) in 5G are reserved for URLLC traffic and the same schedule is repeated over time. The repetition of the same schedule over time makes the slots in the schedules predictable. This, in turn, makes the 5G networks vulnerable to timing attacks. However, the proposed schedule randomization techniques for WirelessHART networks are not applicable for dynamic networks like 5G where the number of flows and the amount of available network resources for URLLC flows vary at runtime. Moreover, the feasibility of the real-time flows need to be guaranteed at runtime. Hence, we propose an online schedule randomization technique that randomizes the slots and the frequencies of the periodic URLLC flows while guaranteeing the feasibility of the flows at runtime.

Multiprocessor hardware platforms are now being considered for embedded systems, due to their high computational power and little additional cost when compared to single processor systems. When scheduling real-time applications on multiprocessor platforms, a possibility is to use global scheduling, where a scheduling algorithm dynamically assign tasks to processors, and tasks can migrate from one processor to another during their execution. In this paper, we tackle the problem of schedulability analysis of sporadic tasks in global scheduling systems, where the scheduler is the earliest deadline first (EDF) algorithm. We provide two main contributions. First, we show that two recently proposed tests perform poorly when the task set contains heavy tasks (i.e. tasks with high utilization). We also show that neither test dominates the other. As a second contribution, we introduce a new schedulability test that improves significantly the percentage of accepted task sets, especially when considering task sets containing heavy tasks. We show the effectiveness of the proposed test through an extensive set of experiments.

Schedulability conditions are used in real-time systems to verify the fulfillment of the temporal constraints of task sets. In this paper, a performance analysis is conducted for the best-known real-time schedulability conditions that can be used in online admission control on uni-processor systems executing under the Rate-Monotonic scheduling policy. Since Liu and Layland introduced the Rate-Monotonic scheduling algorithm, many research studies have been conducted on the schedulability analysis of real-time periodic task sets. However, in most cases, the performance of the proposed schedulability conditions were compared only against the Liu and Layland test and not against the remaining schedulability tests. The goal of this paper is to provide guidelines for system designers in order to decide which schedulability condition provides better performance under different task characteristics. Extensive simulation experiments were conducted to evaluate the inexact schedulability conditions and compare their performance and computational complexity.

In real-time scheduling theory, self-suspension describes the behavior that a job can suspend itself from the ready state and thus be exempted from the scheduling for the suspension duration. This behavior makes it non-trivial to resort to established concepts such as the busy-interval analysis to self-suspending task sets which is required to analyze the worst-case response time of tasks with backlog, e.g., arbitrary-deadline task sets. In this paper, we present a novel suspension-aware busy-interval analysis for dynamic self-suspension tasks where the inter-arrival time of subsequent jobs can be bounded by an arrival curve. Based on the general analysis, we provide worst-case response time analyses and hence sufficient schedulability tests for fixed-priority preemptive uniprocessor scheduling algorithms for arrival-curve constrained and sporadic self-suspension task systems with arbitrary deadlines. Moreover, we provide evaluations based on synthetically generated task sets that show that our method indeed exploits the optimism that is introduced when enlarging the relative deadline of tasks. We demonstrate that our approach improves the state of the art by considering arrival curves that are obtained from tasks with release jitter.

The generalized multiframe task model (GMF) extends the sporadic task model and multiframe task model. Each frame in the GMF model contains an execution time, a relative deadline, and a minimum inter-arrival time. These parameters are fixed after task specification time in the GMF model. However, multimedia and adaptive control systems may be overloaded and no longer stabilized when the task parameters in such systems are not flexible. In order to address this problem, deadlines and periods of frames may change to alleviate temporal overload, e.g., in the parameter adaptation and elastic scheduling model. In this paper, we propose a new model GMF-PA (the GMF model with parameter adaptation). This model allows task parameters to be flexible in arbitrary-deadline systems. A necessary schedulability test based on mixed-integer linear programming is given to check the schedulability under EDF scheduling and optimally assign frame deadlines and periods at the same time. We also prove that the test is a sufficient and necessary schedulability test when frame deadlines and periods must be integers. An approximation algorithm is also deployed to reduce computational running time and indicates a sufficient schedulability test in general. The speed-up factor of our approximation algorithm is $$1+\epsilon $$ where $$\epsilon $$ can be arbitrarily small, with respect to the exact schedulability test of GMF-PA tasks under EDF. We also apply the GMF model to self-suspending tasks. By extending recent work on scheduling self-suspending tasks, we remove the assumption that frame deadlines are equally assigned in self-suspending tasks, and the system is extended from constrained-deadline systems to arbitrary-deadline systems. We have done extensive experiments to show that the schedulability ratio is improved using our techniques in our GMF-PA model.

Summary form only given. Scheduling is crucial in real-time applications. For any real-time system, the desired scheduling policy can be selected based on the scheduling problem itself and the underlying system constraints. This work targets a novel optimization framework which automates the selection and configuration of the scheduling policy. The framework selects the best suited scheduling configuration for a partially specified task set and the given constraints. Our aim is to develop this framework such that the system designer only focuses on the high-level timing behavior of the system, where the implementation choices of the low level timing behavior are taken care of by the framework. The framework fits in the early design phases as a device to automate system synthesis and hide away from the designer the complexity of the underlying runtime environments. In the framework, the system synthesis step involving both analysis and optimization then generates a scheduling solution which at run-time is enforced by the execution environment. This work is a contribution towards a more automated design process building on the wide set of techniques and results developed within the real-time system community.

Traditional fixed-priority scheduling analysis for periodic/sporadic task sets is based on the assumption that all tasks are equally critical to the correct operation of the system. Therefore, every task has to be schedulable under the scheduling policy, and estimates of tasks' worst case execution times must be conservative in case a task runs longer than is usual. To address the significant under-utilization of a system's resources under normal operating conditions that can arise from these assumptions, several mixed-criticality scheduling approaches have been proposed. However, to date there has been no quantitative comparison of system schedulability or run-time overhead for the different approaches. In this dissertation, we present what is to our knowledge the first side-by-side implementation and evaluation of those approaches, for periodic and sporadic mixed-criticality tasks on uniprocessor or distributed systems, under a mixed-criticality scheduling model that is common to all these approaches. To make a fair evaluation of mixed-criticality scheduling, we also address some previously open issues and propose modifications to improve schedulability and correctness of particular approaches. To facilitate the development and evaluation of mixed-criticality applications, we have designed and developed a distributed real-time middleware, called MCFlow, for mixed-criticality end-to-end tasks running on multi-core platforms. The research presented in this dissertation provides the following contributions to the state of the art in real-time middleware: (1) an efficient component model through which dependent subtask graphs can be configured flexibly for execution within a single core, across cores of a common host, or spanning multiple hosts; (2) support for optimizations to inter-component communication to reduce data copying without sacrificing the ability to execute subtasks in parallel; (3) a strict separation of timing and functional concerns so that they can be configured independently; (4) an event dispatching architecture that uses lock free algorithms where possible to reduce memory contention, CPU context switching, and priority inversion; and (5) empirical evaluations of MCFlow itself and of different mixed criticality scheduling approaches both with a single host and end-to-end across multiple hosts. The results of our evaluation show that in terms of basic distributed real-time behavior MCFlow performs comparably to the state of the art TAO real-time object request broker when only one core is used and outperforms TAO when multiple cores are involved. We also identify and categorize different use cases under which different mixed criticality scheduling approaches are preferable.

Mejora de los Test de Planificabilidad para Asignación Incremental de Tareas en Sistemas Multiprocesadores de Tiempo Real

In this paper, we propose a duplication-based algorithm (IDSA) for the integrated scheduling of precedence related real-time tasks with hard and soft deadlines on a set of heterogeneous multiprocessors. We employ a priority-based scheme in which the hard subtasks are always allotted a higher priority as compared to the soft subtasks. IDSA utilizes selective subtask duplication that enables some subtasks to have earlier start times, which results in an increased number of subtasks (and hence task sets) finishing before their deadlines, thereby increasing the schedulability of a real-time application. Our algorithm is also shown to be capable of scheduling a real-time application even if the available number of processors is less than the required number of processors. Based on extensive simulation results, we observe that IDSA offers better success ratio as compared to the existing algorithms in the literature when communication is a dominant factor in the system.

In real-time systems, correctness depends not only on functionality but also on timeliness. A great number of scheduling theories have been developed for verification of the temporal correctness of jobs (software) in such systems. Among them, the Earliest Deadline first until Zero-Laxity (EDZL) scheduling algorithm has received growing attention thanks to its effectiveness in multicore real-time scheduling. However, the true potential of EDZL has not yet been fully exploited in its schedulability analysis as the state-of-the-art EDZL analysis techniques involve considerable pessimism. In this paper, we propose a new EDZL multicore schedulability test. We first introduce an interesting observation that suggests an insight toward pessimism reduction in the schedulability analysis of EDZL. We then incorporate it into a well-known existing Earliest Deadline First (EDF) schedulability test, resulting in a new EDZL schedulability test. We demonstrate that the proposed EDZL test not only has lower time complexity than existing EDZL schedulability tests, but also significantly improves the schedulability of EDZL by up to 36.6 percent compared to the best existing EDZL schedulability tests.

A majority of multi-rate real-time systems are constrained by a multitude of timing requirements, in addition to the traditional deadlines on well-studied response times. This means, the timing predictability of these systems not only depends on the schedulability of certain task sets but also on the timely propagation of data through the chains of tasks from sensors to actuators. In the automotive industry, four different timing constraints corresponding to various data propagation delays are commonly specified on the systems. This paper identifies and addresses the source of pessimism as well as optimism in the calculations for one such delay, namely the reaction delay, in the state-of-the-art analysis that is already implemented in several industrial tools. Furthermore, a generic framework is proposed to compute all the four end-to-end data propagation delays, complying with the established delay semantics, in a scheduler and hardware-agnostic manner. This allows analysis of the system models already at early development phases, where limited system information is present. The paper further introduces mechanisms to generate job-level dependencies, a partial ordering of jobs, which need to be satisfied by any execution platform in order to meet the data propagation timing requirements. The job-level dependencies are first added to all task chains of the system and then reduced to its minimum required set such that the job order is not affected. Moreover, a necessary schedulability test is provided, allowing for varying the number of CPUs. The experimental evaluations demonstrate the tightness in the reaction delay with the proposed framework as compared to the existing state-of-the-art and practice solutions.

This paper focuses on the scheduling of the tasks with hard, soft and non-real-time timing constraints in open real-time systems. It describes a Two-Dimensional Priority Scheduling (TDPS) scheme which not only sets task priority, but also specifies scheduling policy priority. The execution order of a task is determined by both the task priority and its scheduling policy priority. TDPS also supports separating the scheduling mechanism from the scheduling policy. We also enhance TDPS scheme by introducing the CPU utilization bound to each scheduling policy to simplify the schedulability analysis. TDPS scheme can be used to implement different real time systems with different goals (such as hard, soft or hybrid real-time systems) by adjusting the CPU utilization bound of every scheduling policy in runtime. The paper shows through evaluation that TDPS is more open and efficient than the past open real-time scheduling schemes.