Carry-Out Interference Optimization in WCRT Analysis for Global Fixed-Priority Multiprocessor Scheduling

In recent years, the complexity of real-time embedded systems has increased dramatically. For those modern real-time systems, the limitations of original static Response Time Analysis (RTA) become more and more conspicuous. Most static analysis methods not only require much detailed system information, but also only target to some specific system model with non-realistic assumptions. As a result, those methods may produce overly pessimistic results, making them unsuitable to be applied on a complex industrial system. The best system model may be the system itself. Therefore, statistical RTA, which can produce probabilistic analysis results based on samples provided by real systems or simulators, may become more expedient. Statistical RTA usually requires more relaxed assumptions and less system information than static RTA. In this paper, we present an Extreme Value Theory (EVT) based method to compute Worst-Case Response Time (WCRT) targeting complex real-time systems. In the evaluation phase, we have applied this method to the calculation of worst-case transmission delays of messages over Controller Area Network (CAN), and some comparisons with static RTA are also provided. According to the experimental results, as the system complexity increases, our approach performs much more stable and less pessimistic.

The Controller Area Network (CAN) is widely employed in automotive control system networks. In the last few years, the amount of data has been increasing rapidly in these networks. With the purpose of improving CAN bandwidth efficiency, scheduling and analysis are considered to be particularly important. As an effective method, it has been known that assigning offsets to the CAN messages can reduce their worst case response time (WCRT). Meanwhile, the fact is that many commercial CAN controllers have been equipped with a priority or first-in-first-out (FIFO) queue to transmit messages to the CAN bus. However, previous researches for WCRT analysis of CAN messages either assumed a priority queue or did not consider the offset. For this reason, in this paper we propose a WCRT analysis method for CAN messages with assigned offset in the FIFO queue. We first present a critical instant theorem, then we propose two algorithms for WCRT calculation based on the given theorem. Experimental results on generated message sets and a real message set have validated the effectiveness of the proposed algorithms.

The well-known model of Vestal aims to avoid excessive pessimism in the quantification of the processing requirements of mixed-criticality systems, while still guaranteeing the timeliness of higher-criticality functions. This can bring important savings in system costs, and indirectly help meet size, weight and power constraints. This efficiency is promoted via the use of multiple worst-case execution time (WCET) estimates for the same task, with each such estimate characterised by a confidence associated with a different criticality level. However, even this approach can be very pessimistic when the WCET of successive instances of the same task can vary greatly according to a known pattern, as in MP3 and MPEG codecs or the processing of ADVB video streams. In this paper, we present a schedulability analysis for the multiframe mixed-criticality model, which allows tasks to have multiple, periodically repeating, WCETs in the same mode of operation. Our work extends both the analysis techniques for Static Mixed-Cricality scheduling (SMC) and Adaptive Mixed-Criticality scheduling (AMC), on one hand, and the schedulability analysis for multiframe task systems on the other. Our proposed worst-case response time (WCRT) analysis for multiframe mixed-criticality systems is considerably less pessimistic than applying the SMC, AMC-rtb and AMC-max tests obliviously to the WCET variation patterns. Experimental evaluation with synthetic task sets demonstrates up to 63.8% higher scheduling success ratio (in absolute terms) compared to the best of the frame-oblivious tests.

In this paper, the scheduling issue of periodic tasks with task dependencies is discussed. A feedback scheduler with frequency actuator and performance index is presented. Worst-case response time analysis that affects the real-time deadline miss ratio is analyzed. With the proposed scheduler, the schedulability of periodic tasks that have varied frequencies can be enhanced in the context of real-time control systems. Examples show that, this feedback scheduler can achieve high CPU utilization and guarantee a certain deadline miss ratio in real-time control systems without sacrificing the system stability

How to support real-time traffic of important aperiodic messages using Foundation Fieldbus (FF) is investigated in this paper. An integrated worst-case response time (WCRT) analysis of aperiodic message indicates FF can't effectively guarantee real-time traffic of important aperiodic message despite FF providing such mechanisms as PT (Pass Token) priority and PT rotation period, etc. After finding the cause of current mechanism' deficiency, an improved mechanism proposed and validated with simulation in this paper. Further, some conclusions such as ongoing work are provided in this paper.

In scheduling algorithms based on the Rate Monotonic (RM) method which are widely used in development of real-time systems, tasks with shorter periods have higher priorities. In contrast, ones with longer periods are likely to suffer from increased response times and jitter due to their lower priorities. We propose an Execution Right Delegation (ERD) method based on RM where a high-priority server for particular (or important) task is introduced to shorten response time and jitter of the task. In the evaluation, it is confirmed that response times and jitter of a particular (important) task are reduced. We also show Response Time Analysis (RTA), which assures worst-case response time of the task. This paper shows the algorithm and RTA of ERD and evaluates it by comparing it to a Deadline Monotonic method. The evaluation by simulation shows that ERD can reduce the average worst-case response time by 13.45% at maximum compared to the Deadline Monotonic scheduling. In addition, we confirm that the RTA provides a worst-case response time close to the simulation results.

For priority based buses such as CAN, worst case response time analysis is able to determine whether messages always meet their deadlines. This can include system models with bounded network faults. However the worst-case scenario (the critical instant) used by the analysis is extremely pessimistic compared to the rest of the invocations in the hyperperiod. We use weakly hard constraints to provide upper bounds on the maximum number of missed deadlines under fault conditions. By allowing some deadlines to be missed (around the critical instant) the weakly-hard schedulability of the system can be guaranteed at much higher levels of faults. This paper presents a response time based formulation that provides a guarantee on the weakly-hard schedulability of messages. Simulation results based on CAN and the Latest Send Time-CAN protocol show that because of the pessimism of the approach, in fact almost all messages meet their deadlines.

Queue assignment for fixed-priority real-time flows in time-sensitive networks: Hardness and algorithm

A number of methods have been proposed for the response-time analysis (RTA) of controller area networks (CANs), which are the industry standard for in-vehicle network protocols. However, most of these methods are unsuitable for analyzing nonperiodically transmitted messages because they assume a constant transmission period for each message. Moreover, the calculated evaluation criteria are limited and comprise many over-pessimistic estimations, such as the worst-case response time (WCRT). To tackle these problems, this paper proposes an RTA method for CANs with randomly occurring messages, which replaces the constant transmission period with the average number of transmission instances per unit time. This approach finds the approximate probability distribution of the response time to any message in a CAN, providing a more general measure than the WCRT. To this end, a mathematical model based on M/G/1 queueing theory is developed. The model accurately emulates the behavior of nonperiodic CAN messages and enables RTA with minimal pessimistic estimations. When tested against the benchmarks, the proposed method accurately obtained response time distributions within several seconds to several tens of seconds.

The group-based preemptive scheduling provides a flexible mechanism to define the preemptive relations between tasks. However, this scheduling scheme together with a resource access synchronization protocol and requirements of fault tolerance makes the predication of a real-time system's behaviors more difficult than traditional scheduling scheme. The major contribution of our work is an algorithm to calculate the worst-case response time for tasks under the fault-tolerant group-based preemptive scheduling. We first present the algorithm assuming that no task suffers any error. Then the algorithm is extended to consider a fault model and a primary/alternative fault-tolerant mechanism. Based on the tasks' worst-case response time, the schedulability of a given task set can be determined. Moreover, we also introduce a method to calculate the minimum allowed time between two consecutive faults.

Despite the potential of quantum computing for drastically accelerating suitable real-time applications, response time analysis is still required to guarantee that quantum programs running on quantum computers satisfy application-specific timing requirements. This paper describes an inaugural project to determine whether a quantum program running on a quantum computer satisfies the timing constraints of a realtime application, that is, is quantum computing punctual and reliable in this time-sensitive application domain? Can this timing guarantee be formally verified? We leverage the existing work on the functional reactive programming (FRP) model to predict the worst-case response time (WCRT) of fault-tolerant classical computing systems since the timing analysis of re-executions for fault recovery plus transient-faults-induced wasted execution times is similar to determining the response time of FRP tasks. Ongoing work shows that accounting for wasted execution times due to errors in quantum computers resulting from quantum decoherence and state fidelity can be treated similarly and develops a mapping from quantum programs to FRP programs for efficient timing analysis.

We propose an end-to-end approach to scheduling tasks that share resources in a multiprocessor or distributed systems. In our approach, each task is mapped into a chain of subtasks, depending on its resource accesses. After each subtask is assigned a proper priority, its worst-case response time can be bounded. Consequently the worst-case response time of each task can be obtained and the schedulability of each task can be verified by comparing the worst-case response time with its relative deadline. >

With the rapid development of parallel programming techniques and the widespread use of multiprocessors, scheduling and analysis techniques supporting parallel real-time tasks become a critical topic for multiprocessor real-time systems. Global scheduling that allows the vertices of a parallel task to execute on any processor is a promising scheduling approach with guaranteed theoretical bounds and wide use in practice. However, the complex internal structure of parallel tasks leads to extensive inner- and inter-task interference, which leads to significant pessimism in the worst-case timing analysis. In this paper, a global fixed-priority (G-FP) scheduling with constrained parallelism for parallel real-time tasks based on the sporadic directed acyclic graph (DAG) model is proposed. Each DAG task is assigned a parallel threshold, such that the number of processors occupied by the task is limited to the parallel threshold of the task at a time. We propose a heuristic algorithm to set the parallel threshold and present a response-time analysis (RTA) to exploit the feature of the constrained parallel scheduling. Experiments with randomly generated tasks show that the proposed approach improves the schedulability upon G-FP and federated scheduling in terms of acceptance ratio.

Traditional methods rely on Static Timing Analysis techniques to compute the Worst Case Response Time for tasks in real-time systems. Multi-Core real-time systems are faced up with concurrent task executions, semaphore accesses, and task migrations where it may be difficult to obtain the worst case upper bound. A new three staged probabilistic estimation concept is presented. Worst Case Response Times are estimated for tasksets which consist of tasks with multiple time bases. The concept involves data generation with sample classification and sample size equalization, model fit and Worst Case Response Time estimation on the basis of extreme value distribution models. A Generalized Pareto Distribution model fit method which includes threshold detection and parameter estimation is also presented. Sample classification in combination with the new Generalized Pareto Distribution model fit method allows to estimate Worst Case Response Times with low pessimism ranges compared to estimation methods that uses the Generalized Pareto or the Gumbel max distribution without sample classification.

The worst-case response time of the message and busload are the main parameters in scheduleability analysis for the Controller Area Network (CAN) bus. This paper gives the probability distribution curves of stuffed bits in message's different length by introducing the probability model of stuffed bits. It obtains the maximum stuffed bits under a given probability P, to reduce pessimism of the worst-case response time and busload value. Taking it as a theoretical guide, and we design and develop scheduling analysis software on fixed priority message scheduling. Then we use the software to analysis the scheduleability for the messages in a Hybrid Electric Vehicle. Furthermore, a simulation experiment based on CANoe was made to test the design. By comparing the results, it shows that algorithm, as we introduced, based on the probability model of stuffed bits is right, and the designed software is accurate and reliable.