Replication management in reliable real-time systems

Building reliable real-time applications on top of commercial off-the-shelf (COTS) components is not a straightforward task. Thus, it is essential to provide a simple and transparent programming model, in order to abstract programmers from the low-level implementation details of distribution and replication. However, the recent trend for incorporating pre-emptive multitasking applications in reliable real-time systems inherently increases its complexity. It is therefore important to provide a transparent programming model, enabling pre-emptive multitasking applications to be implemented without resorting to simultaneously dealing with both system requirements and distribution and replication issues. The distributed embedded architecture using COTS components (DEAR-COTS) architecture has been previously proposed as an architecture to support real-time and reliable distributed computer-controlled systems (DCCS) using COTS components. Within the DEAR-COTS architecture, the hard real-time subsystem provides a framework for the development of reliable real-time applications, which are the core of DCCS applications. This paper presents the proposed framework, and demonstrates how it can be used to support the transparent replication of software components.

Queuing and routing in a hierarchical powerline communication system

Although power-line communication (PLC) is not a new technology, its use to support data communication with timing requirements is still the focus of ongoing research. A new infrastructure intended for communication using power lines from a central location to dispersed nodes using inexpensive devices was presented recently. This new infrastructure uses a two-level hierarchical power-line system, together with an IP-based network. Due to the master-slave behaviour of the PLC medium access, together with the inherent dynamic topology of power-line networks, a mechanism to provide end-to-end communication through the two levels of the power-line system must be provided. In this paper we introduce the architecture of the PLC protocol layer that is being implemented for this end.

A power line communication stack for metering, SCADA and large-scale domotic applications

This paper describes the communication stack of the REMPLI system: a structure using power-lines and IPbased networks for communication, for data acquisition and control of energy distribution and consumption. It is furthermore prepared to use alternative communication media like GSM or analog modem connections. The REMPLI system provides communication service for existing applications, namely automated meter reading, energy billing and domotic applications. The communication stack, consisting of physical, network, transport, and application layer is described as well as the communication services provided by the system. We show how the peculiarities of the power-line communication influence the design of the communication stack, by introducing requirements to efficiently use the limited bandwidth, optimize traffic and implement fair use of the communication medium for the extensive communication partners.

INDEPTH: timeliness assessment of ethernet/IP-based systems

The continuous improvement of Ethernet technologies is boosting the eagerness of extending their use to cover factory-floor distributed real time applications. Indeed, it is remarkable the considerable amount of research work that has been devoted to the timing analysis of Ethernet-based technologies in the past few years. It happens, however, that the majority of those works are restricted to the analysis of sub-sets of the overall computing and communication system, thus without addressing timeliness in a holistic fashion. To this end, we address an approach, based on simulation, aiming at extracting temporal properties of commercial-off-the-shelf (COTS) Ethernet-based factory-floor distributed systems. This framework is applied to a specific COTS technology, Ethernet/IP. We reason about the modeling and simulation of Ethernet/IP-based systems, and on the use of statistical analysis techniques to provide useful results on timeliness. The approach is part of a wider framework related to the research project INDEPTH NDustrial-Ethernet ProTocols under Holistic analysis.

Timeliness in COTS factory-floor distributed systems: What role for simulation?

In the past few years, a significant amount of work has been devoted to the timing analysis of Ethernet-based technologies. However, none of these address the problem of timeliness evaluation at a holistic level. This paper describes a research framework embracing this objective. It is advocated that, simulation models can be a powerful tool, not only for timeliness evaluation, but also to enable the introduction of less pessimistic assumptions in an analytical response time approach, which, most often, are afflicted with simplifications leading to pessimistic assumptions and, therefore, delusive results. To this end, we address a few inter-linked research topics with the purpose of setting a framework for developing tools suitable to extract temporal properties of commercial-off-the-shelf (COTS) factory-floor communication systems.

Reliable real-time communication in CAN networks

Controller area network (CAN) is a fieldbus network suitable for small-scale distributed computer controlled systems (DCCS), being appropriate for sending and receiving short real-time messages at speeds up to 1 Mbit/sec. Several studies are available on how to guarantee the real-time requirements of CAN messages, providing preruntime schedulability conditions to guarantee the real-time communication requirements of DCCS traffic. Usually, it is considered that CAN guarantees atomic multicast properties by means of its extensive error detection/signaling mechanisms. However, there are some error situations where messages can be delivered in duplicate or delivered only by a subset of the receivers, leading to inconsistencies in the supported applications. In order to prevent such inconsistencies, a middleware for reliable communication in CAN is proposed, taking advantage of CAN synchronous properties to minimize the runtime overhead. Such middleware comprises a set of atomic multicast and consolidation protocols, upon which the reliable communication properties are guaranteed. The related timing analysis demonstrates that, in spite of the extra stack of protocols, the real-time properties of CAN are preserved since the predictability of message transfer is guaranteed.

An architecture for reliable distributed computer-controlled systems

In Distributed Computer-Controlled Systems (DCCS), both real-time and reliability requirements are of major concern. Architectures for DCCS must be designed considering the integration of processing nodes and the underlying communication infrastructure. Such integration must be provided by appropriate software support services. In this paper, an architecture for DCCS is presented, its structure is outlined, and the services provided by the support software are presented. These are considered in order to guarantee the real-time and reliability requirements placed by current and future systems.

Integrating inaccessibility in response time analysis of CAN networks

Controller Area Network (CAN) is a fieldbus network suitable for small-scale Distributed Computer Controlled Systems, being appropriate for transferring short real-time messages. Nevertheless, it must be understood that the continuity of service is not fully guaranteed, since it may be disturbed by temporary periods of network inaccessibility [1]. In this paper, such temporary periods of network inaccessibility are integrated in the response time analysis of CAN networks. The achieved results emphasise that, in the presence of temporary periods of network inaccessibility, a CAN network is not able to provide different integrity levels to the supported applications, since errors in low priority messages interfere with the response time of higher priority message streams.

Programming atomic multicasts in CAN

In Distributed Computer-Controlled Systems (DCCS), a special emphasis must be given to the communication infrastructure, which must provide timely and reliable communication services. CAN networks are usually suitable to support small-scale DCCS. However, they are known to present some reliability problems, which can lead to an unreliable behaviour of the supported applications. In this paper, an atomic multicast protocol for CAN networks is proposed. This protocol explores the CAN synchronous properties, providing a timely and reliable service to the supported applications. The implementation of such protocol in Ada, on top of the Ada version of Real-Time Linux is presented, which is used to demonstrate the advantages and disadvantages of the platform to support reliable communications in DCCS.

Replica management in real-time Ada 95 applications

In this paper, we present some of the fault tolerance management mechanisms being implemented in the Multi-μ architecture, namely its support for replica non-determinism. In this architecture, fault tolerance is achieved by node active replication, with software based replica management and fault tolerance transparent algorithms. A software layer implemented between the application and the real-time kernel, the Fault Tolerance Manager (FTManager), is the responsible for the transparent incorporation of the fault tolerance mechanisms The active replication model can be implemented either imposing replica determinism or keeping replica consistency at critical points, by means of interactive agreement mechanisms. One of the Multi-μ architecture goals is to identify such critical points, relieving the underlying system from performing the interactive agreement in every Ada dispatching point.

Mobilidade transnacional e competências profissionais: um estudo de caso com alunos envolvidos no Programa Erasmus

Dissertação de mestrado em Ciências da Educação: área de Educação e Desenvolvimento

Multi-μ: an Ada 95 based architecture for fault tolerance support of real-time systems

This paper presents an architecture (Multi-μ) being implemented to study and develop software based fault tolerant mechanisms for Real-Time Systems, using the Ada language (Ada 95) and Commercial Off-The-Shelf (COTS) components. Several issues regarding fault tolerance are presented and mechanisms to achieve fault tolerance by software active replication in Ada 95 are discussed. The Multi-μ architecture, based on a specifically proposed Fault Tolerance Manager (FTManager), is then described. Finally, some considerations are made about the work being done and essential future developments.

A feedback-based decentralised coordination model for distributed open real-time systems

Moving towards autonomous operation and management of increasingly complex open distributed real-time systems poses very significant challenges. This is particularly true when reaction to events must be done in a timely and predictable manner while guaranteeing Quality of Service (QoS) constraints imposed by users, the environment, or applications. In these scenarios, the system should be able to maintain a global feasible QoS level while allowing individual nodes to autonomously adapt under different constraints of resource availability and input quality. This paper shows how decentralised coordination of a group of autonomous interdependent nodes can emerge with little communication, based on the robust self-organising principles of feedback. Positive feedback is used to reinforce the selection of the new desired global service solution, while negative feedback discourages nodes to act in a greedy fashion as this adversely impacts on the provided service levels at neighbouring nodes. The proposed protocol is general enough to be used in a wide range of scenarios characterised by a high degree of openness and dynamism where coordination tasks need to be time dependent. As the reported results demonstrate, it requires less messages to be exchanged and it is faster to achieve a globally acceptable near-optimal solution than other available approaches.

Real-time scheduling of parallel tasks in the Linux Kernel

This paper proposes a global multiprocessor scheduling algorithm for the Linux kernel that combines the global EDF scheduler with a priority-aware work-stealing load balancing scheme, enabling parallel real-time tasks to be executed on more than one processor at a given time instant. We state that some priority inversion may actually be acceptable, provided it helps reduce contention, communication, synchronisation and coordination between parallel threads, while still guaranteeing the expected system’s predictability. Experimental results demonstrate the low scheduling overhead of the proposed approach comparatively to an existing real-time deadline-oriented scheduling class for the Linux kernel.

Supporting real-time parallel task models with work-stealing

Dynamic parallel scheduling using work-stealing has gained popularity in academia and industry for its good performance, ease of implementation and theoretical bounds on space and time. Cores treat their own double-ended queues (deques) as a stack, pushing and popping threads from the bottom, but treat the deque of another randomly selected busy core as a queue, stealing threads only from the top, whenever they are idle. However, this standard approach cannot be directly applied to real-time systems, where the importance of parallelising tasks is increasing due to the limitations of multiprocessor scheduling theory regarding parallelism. Using one deque per core is obviously a source of priority inversion since high priority tasks may eventually be enqueued after lower priority tasks, possibly leading to deadline misses as in this case the lower priority tasks are the candidates when a stealing operation occurs. Our proposal is to replace the single non-priority deque of work-stealing with ordered per-processor priority deques of ready threads. The scheduling algorithm starts with a single deque per-core, but unlike traditional work-stealing, the total number of deques in the system may now exceed the number of processors. Instead of stealing randomly, cores steal from the highest priority deque.