Jörn Migge

Aperiodic traffic in response time analyses with adjustable safety level

In distributed real-time systems it is crucial to ensure the temporal validity of the data exchanged among the nodes. Classically, the frame worst case response time (WCRT) analyses, and the software tools which implement them, do not take into account the aperiodic traffic. One of the main reasons for this is that the aperiodic traffic is generally very difficult to characterize (i.e., the arrival patterns of the aperiodic frames). The consequence of this is that one tends to underestimate the WCRT, which may have an impact on the overall safety of the system. In this paper, we propose a probabilistic approach to model the aperiodic traffic and integrate it into response time analysis. The approach allows the system designer to choose the safety level of the analysis based on the systems dependability requirements. Compared to existing deterministic approaches the approach leads to more realistic WCRT evaluation and thus to a better dimensioning of the hardware platform.

An efficient and simple class of functions to model arrival curve of packetised flows

Network Calculus is a generic theory conceived to compute upper bounds on network traversal times (WCTT -- Worst Case Traversal Time). This theory models traffic constraints and service contracts with arrival curves and service curves. As usual in modelling, the more realistic the model is, the more accurate the results are, however a detailed model implies large running times which may not be the best option at each stage of the design cycle. Sometimes, a trade-off must be found between result accuracy and computation time. This paper proposes a combined use of two simple class of curves in order to produce accurate results with a low computational complexity. Experiments are then conducted on a realistic AFDX case-study to benchmark the proposal against two existing approaches.

Timing analysis of compound scheduling policies: application to posix1003.1b

The analysis of fixed priority preemptive scheduling has been extended in various ways to improve its usefulness for the design of real-time systems. In this paper, we define the layered preemptive priority scheduling policy which generalizes fixed preemptive priorities by combination with other policies in a layered structure. In particular, the combination with the Round Robin scheduling policy is studied. Its compliance with Posix 1003.1b requirements is shown and its timing analysis is provided. For this purpose and as a basis for the analysis of other policies, the concept of majorizing work arrival function, is introduced to synthesize essential ideas used in existing analysis of the fixed preemptive priority policy.If critical resources are protected by semaphores, the Priority Ceiling Protocol (PCP) can be used under fixed preemptive priorities to control resulting priority inversions. An extension of the PCP is proposed for Round Robin, to allow a global control of priority inversions under the layered priority policy and to prevent deadlocks. The initial timing analysis is extended to account for the effects of the protocol. The results are illustrated by a small test case.

Dual-Priority versus Background Scheduling: A Path-Wise Comparison

In this paper, two well-known scheduling policies for real-time systems, namely background scheduling (BS) and dual-priority (DP) are compared in terms of response times for soft real-time traffic (SRT). It is proved in the preemptive as well as in the non-preemptive case that, when the SRT traffic is FIFO, the DP policy always outperforms BS for all instances of SRT tasks. When the SRT traffic is not FIFO but if all tasks are of equal size then, in the non-preemptive case, the average response times is shown to be always better under DP than under BS. As a complementary result, some non-FIFO examples where BS behaves better than DP for some SRT tasks but also on the average of the SRT response times, are given. The proofs are based on a trajectorial method that may be used for comparing other scheduling policies.

Pre-shaping Bursty Transmissions under IEEE802.1Q as a Simple and Efficient QoS Mechanism

The automotive industry is swiftly moving towards Ethernet as the high -speed communication network for in-vehicle communication. There is nonetheless a need for protocols that go beyond what standard Ethernet has to offer in order to provide additional QoS to demanding applications such as ADAS systems (Advanced Driver -Assistance Systems) or audio/video streaming. The main protocols currently considered for that purpose are IEEE802.1Q, AVB with the Credit Based Shaper mechanism (IEEE802.1Qav) and TSN with its Time -Aware Shaper (IEEE802.1Qbv). AVB/CBS and TSN/TAS both provide efficient QoS mechanisms and they can be used in a combined manner, which offers many possibilities to the designer. Their use however requires dedicated hardware and software components, and clock synchronization in the case of TAS. Previous studies have also shown that the efficiency of these protocols depends much on the application at hand and the value of the configuration par ameters. In this work, we explore the use of “pre-shaping” strategies under IEEE802.1Q for bursty traffic such as audio/video streams as a simple and efficient alternative to AVB/CBS and TSN/TAS. Pre -shaping means inserting on the sender side “well -chosen” pauses between successive frames of a transmission burst (e.g., as it happens when sending a camera frame), all the other characteristics of the traffic remaining unchanged. We show on an automotive case -study how the use of pre-shaping for audio/video streams leads to a drastic reduction of the communication latencies for the best effort streams while enabling meeting the timing constraints for the rest of the traffic. We then discuss the limitations of the pre-shaping mechanism and what is needed to faci litate its adoption.