A pre-run-time scheduling algorithm for object-based distributed real-time systems

Abstract

The most important goal in hard real-time systems is to guarantee that all timing constraints are satisjied. Even though object-based techniques (which contain reusable software components) are used to manage the complexity in the software development process of such systems, execution ejjiciency may have to be sacrijiced, due to the large number ofprocedure calls and contention for accessing sopware components. These issues are addressed by the forlowing parallelizing techniques: (a) converting potentially inejticient procedure calls to a source of concurrency via asynchronous remote procedure calls (ARPC) (b) replicating (or cloning) software components to reduce the contention. The existing object-based scheduling algorithms construct an initial schedule and apply incremental parallelization techniques to modifit the initial schedule till a feasible schedule is generated. But these algorithms are applicable for scheduling only multiple independent tasks. This paper describes a pre-run-time scheduling algorithm for a set of periodic object-based tasks having precedence constraints among them. The algorithm employs parallelism exploitation techniques to guarantee timeliness in almost fully predictable environments such as factory automation, aerospace, and avionics. It allocates the components of object-based periodic tasks to the sites of a distributed system based on a clustering heuristic which takes into account the ARPC parallelism and load balancing, and schedules them on respective sites. The algorithm also finds a schedule for communication channel(s) and clones the components of object-based periodic tasks, i f contention occurs in accessing them. In addition to the above (periodicity and precedence) constraints, the tasks handled by our algorithm can have resource constraints among them. The experimental evaluation of the algorithm shows that the combination 'This work was supported by the Department of Science and Technology, New Delhi. of the proposed clustering heuristic and cloning enhances schedulability.

A hierarchical distributed object-oriented architecture for energy management system

“…Techniques that try to exploit the parallelism inherent among the objects can help overcome these disadvantages. Two such techniques applied in this proposed architecture are i) cloning and ii) asynchronous remote procedure calls (ARPCs) [10,11,12]. Cloning: The technique of cloning is resolving contention among ADTs by replicating the software component on another processor so that more than one data item can be processed at a same time.…”

“…An overview of a careful systematic analysis of allocation problem is as follows [10,11,12]: A) Constructing Comprehensive Entity Invocation Graph: A comprehensive entity invocation graph (CEIG) gives a clear picture of the communicating methods and the communication sequence. Constructing a CEIG for the path is the first step in identifying the clustering possibilities of the various methods.…”

“…Following is a heuristic proposed in [10] to calculate the net gain/loss while making a clustering decision:…”

“…This could lead to missed deadlines in task execution at real-time [4,9]. Task-scheduling algorithms [2,8,9,10,11,12] have been proposed in real-time system literature that overcome the above problems with respect to performance by effectively scheduling the operation of different software components. This work attempts to apply object-based real-time task scheduling in an EMS in a distributed multi-processor environment.…”

“…This work attempts to apply object-based real-time task scheduling in an EMS in a distributed multi-processor environment. Having the object-oriented model of the EMS applications in hand, a systematic analysis towards allocation and scheduling of each of the software components/methods to the different processors is performed based on well-established algorithms [8][9][10][11][12]. This paper provides a detailed treatment of the background material along with an illustration of the application of the above concepts with the aid of object-based model of a few sample EMS applications.…”