This paper presents a proposal to integrate a generic technique to express complex scheduling and timing parameters of distributed transactions as a part of the Distributed Systems Annex of Ada (DSA). The technique allows real-time middleware implementations to change their scheduling policies for both the processing nodes and the networks with a minimal interference in the application code. The proposed mechanisms are managed by the middleware in a transparent way. The only requirement is an initial configuration operation, which can be generated automatically, and a single operation call to set an event identifier in each of the tasks that initiates a distributed transaction. The automatic process used to obtain the initial configuration of the distributed application, based on a real-time model, is also proposed. The implementation of this proposal is currently being developed.
Two current trends in the real-time and embedded systems are the multiprocessor architectures and the partitioning technology that enables several isolated applications with different criticality levels to share the same computer. This paper presents a real-time platform for multiprocessor and partitioned systems, in which communication requirements are also considered. The paper describes the adaptation of MaRTE OS (a monoprocessor real-time operating system) to the XtratuM hypervisor for the multiprocessor Intel x86 architecture. This adaptation makes two contributions to ease the development process of future mixed-criticality applications: firstly, it integrates the hypervisor technology and the fully partitioned scheduling in a multiprocessor environment, and secondly, it provides the basis to interconnect partitioned and non-partitioned applications via a homogeneous communication subsystem.• Clock and timer management. Because clocks and timers are shared by all the partitions, MaRTE OS must access these services through the appropriate hypercalls. Although XtratuM provides support for two different clocks (a global monotonic clock and a local execution time clock for each virtual CPU), this first adaptation only uses the global clock and leaves the integration of the remaining clock for future work. INTERPARTITION COMMUNICATION EVALUATIONThis section aims at validating the proposed interpartition communication subsystem. To better evaluate its performance, a set of tests has been executed without using other high-level network protocols such as UDP/IP on top of our approach.The tests will measure the communication latency associated with a data flow between two partitions (i.e. the first partition writes data samples and the second partition reads them). The communication latency is defined as the time between the transmission and the reception of each data sample. This performance analysis includes two case-studies, which are detailed in the following: Overhead testThe first case-study aims at measuring the overhead of using the proposed interpartition communication subsystem on top of the hypervisor. To this end, the test defines one single data flow from partition 1 to partition 2 and with one disjoint core allocated to each partition. The test is executed with different payloads and two configurations: (1) by directly using the communication services provided by XtratuM and (2) through the interpartition communication subsystem implemented in MaRTE OS.The maximum latencies obtained for the Overhead test are reported in Figure 12. As can be observed, the interpartition communication subsystem adds an overhead lower than 15 ms to the communication services provided by XtratuM. This overhead can be explained by the software layer added to use the interpartition communication subsystem as a standard driver in MaRTE OS and the extra overhead in the handling of interrupts by the operating system. Finally, it is worth noting that maximum latencies are nearly constant for the selected payloads in both cases, ...
<p>El uso de middleware de distribución facilita la programación de sistemas distribuidos de tiempo real heterogéneos, y por extensión también puede facilitar la generación automática de código como parte de una estrategia de desarrollo basada en modelos. Sin embargo, esta clase de middleware presenta una complejidad añadida que dificulta su uso en sistemas con ciertos requisitos de criticidad o de tiempo real. En este trabajo se hace una revisión de algunos estudios previos en los que se muestra la posibilidad de utilizar un middleware de distribución centrado en los datos (DDS, Data Distribution Service) para la integración de aplicaciones con criticidad mixta en sistemas distribuidos.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.