A Novel Real Time Scheduling Frame-work for CORBA-Based Applications.

Abstract

Many real-time application domains can benefit from flexible and open distributed architectures, such as those defined by the CORBA specification. Although CORBA is well-suited for conventional request/response applications, it is not yet suitable for realtime applications due to the lack of key Quality of Service (QoS) features and performance optimizations. This paper explains the design and implementation of a real-time scheduling service that can provide QoS guarantees for deterministic real-time CORBA applications. The scheduling service deals with multiprocessor task scheduling in a distributed environment. It involves a global scheduler and a local scheduler. The global scheduler schedules the tasks based on the Schedulability analysis and the request priority of the tasks. It uses genetic algorithms for intelligent multiprocessor scheduling of the tasks. The Run-Time Scheduler or the Local Scheduler maps client requests for particular servant operations into priorities that are understood by the local OS dispatcher. This Real-time Scheduling Service is implemented as a CORBA object that is responsible for allocating system resources to meet the QoS needs of the applications. It thus brings about extensibility and interoperability in a distributed object system.