Enhancing the Performance of Distributed Real-Time Systems

Advanced embedded systems can consist of many sensors, actuators and processors that aredeployed on one or several boards, while having a demand of interacting with each other andsharing resources. Communication between different components usually has strict timingconstraints. There is thus a strong need to provide solutions for time critical communication.This thesis focuses on both the support of real-time services over standard switched Ethernetnetworks and the improvement of systems\u27 real-time characteristics, such as reducing delay andjitter in processors and on communication links. Switched Ethernet has been chosen in this work because of its major advantages inindustry; it supports higher bit-rates than most other current LAN (Local Area Network)technologies, including field buses, still at a low cost. We propose using a star network topologywith a single Ethernet switch. Each node is connected to a separate port of the switch via a fullduplexlink, thereby eliminating collisions. A solid real-time communication protocol forswitched Ethernet networks is proposed in the thesis, including a real-time layer between theEthernet layer and the TCP/IP suite. The network has the capability of supporting both real-timeand non real-time traffic and assuring adaptation to the surrounding protocol standards. Most embedded systems work in a dynamic environment, where the precise behavior ofthe network traffic can usually not be predicted. To support real-time services, we have chosenthe Earliest Deadline First scheduling algorithm (EDF) because of its optimality, high efficiencyand suitability for being used in adaptive schemes. To be able to increase the amount ofguaranteed real-time traffic, the notion of Asymmetric Deadline Partitioning Scheme (ADPS) isintroduced. ADPS allows distribution of the end-to-end deadline of a message, sent from anysource node in the network to any destination node via the switch, into two sub-deadlines, onefor each hop according to the load of the physical link that it must traverse. For the EDF scheduling algorithm, the feasibility test is one of the most importanttechniques that provides us with information about whether or not the real-time traffic can beguaranteed by the network. With the same computational complexity as the feasibility test, amethod has been developed to compute the minimum EDF-feasible deadline for a real-timetask. The importance of this method in real-time applications lies in that it can be effectivelyused to reduce the response times of specific control activities or limit their input-output jitter.To allow more flexibility in the control of delay and jitter in real-time systems, a generalapproach for reducing task deadlines according to the requirements of individual tasks has beendeveloped. The method allows the user to specify a deadline reduction factor for each task inorder to better exploit the available slack according to the tasks\u27 actual requirements