Prabha Gopinath

Object-oriented real-time systems: concepts and examples

The problems associated with developing real-time software systems, including ensuring predictable real-time behavior under both normal and abnormal operating conditions, are outlined. The management of temporal complexity, structuring of dynamic real-time applications, object-oriented models, object-oriented real-time languages, and the requirements for real-time object-oriented models are discussed. Chaos, an object-based language and programming/execution paradigm designed for dynamic real-time applications, is described.<<ETX>>

Applying compiler techniques to scheduling in real-time systems

Worst-case scheduling techniques for real-time applications often result in sever underutilization of the processor resources since most tasks finish in much less time than their anticipated worst-case execution times. A description is presented of compiler-based techniques that classify the application code on the basis of predictability and monotonicity, introduce measurement code fragments at selected points in the application code, and use the results of run-time measurements to dynamically adapt worst-case schedules. This results in better utilization of the system and early failure detection and recovery.<<ETX>>

Object-oriented design of real-time software

An examination is made of the ability of the object-oriented model to represent and encapsulate the temporal characteristics of adaptable, real-time software. The differences between object-oriented design and the more traditional function-oriented design of real-time systems are briefly reviewed. The various temporal characteristics present in a real-time, object-oriented system and techniques for the design of object-oriented real-time software are examined. The many open problems in the area are discussed. The object-oriented model and many of the concepts described have been used in the implementation of the control software for an experimental robotics project.<<ETX>>

CHAOS: why one cannot have only an operating system for real-time applications

CHAOS ― A Concurrent Hierarchical Adaptable Object System, is a complete programming and operating system. Its goal is to support the programming of real-time applications that are accountable, efficient, and predictable

A Hierarchical Approach to Load Balancing in Distributed Systems

In this paper we present a hierarchical algo- rithm for performing dynamic load balancing in a distri- buted system The processors in the system are viewed as being in a lightly loaded, heavily loaded, or normally loaded state The goal of the algorithm is to keep all nodes normally loaded by migrating processes from heavily loaded nodes to lightly loaded nodes In addi- tion, the load balancing must involve low communica- tion overhead and respond quickly to load imbalance in the system The system is partitioned into disjoint groups of processors First intra-partition process migra- tion is performed to achieve an acceptable load distribu- tion If this is not sufficient, inter-partition load balanc- ing is carried out

Correlation analysis techniques for refining execution time estimates of real-time applications

Scheduling techniques based upon worst case execution times, as are commonly used in real-time applications, often result in severe underutilization of the processor resources since most tasks finish in much less time than their anticipated worst-case execution times. We describe techniques for identifying correlation among the executions of various statements within a program. We demonstrate how this information can be used to refine the estimate of remaining worst case execution time of a real-time task as the execution of the task progresses. Refined estimates can be used at run-time to achieve better utilization, of the system and early failure detection and recovery.<<ETX>>

Representation and execution support for reliable robot applications

Robot applications, represented as plans, are used to outline a viewpoint that robustness needs to be emphasized in two areas: in the plan representation and in the underlying system software. Robot applications are inherently distributed, since the hardware usually comprises a set of independent actuators and sensors, with the robot programs acting as links between them. A special model of distributed computation, the RS (Robot Schemas) model, has been designed to handle the issues of robot plan representation, and an overview of the model is presented. An initial implementation of the model with minimal execution support demonstrated that the domain-dependent aspect of robustness on its own was not sufficient for robust behavior. Consequently, the OS has been augmented with real-time scheduling, and monitoring facilities.<<ETX>>

Robust representation and execution of robot plans

The construction of real-time software for autonomous robot systems that can operate in an uncertain and dynamic environment is considered. Techniques for representing robust robot plans using the RS (robot schema) model are developed which make it possible to separate planned decision-making from error monitoring; they give a modular way to embed error detection, diagnosis, and recovery into plans, and via the formal tools of RS they allow one to analyze plans for error behavior. However, experience in implementing the RS kernel leads to the conclusion that robustness in the plan representation alone is not sufficient. Robustness must also be incorporated in the underlying system software to complement robustness in the plan representation model. Experiences with the initial implementation of the RS execution environment kernel also emphasized the need for operating system constructs that would support the robustness inherent in the model.<<ETX>>

Opportunistic evaluation of communication link loads

Algorithms for measuring the loads on the communication links in a distributed system are presented. Timestamped messages are used to measure latencies across physical and virtual links in the system. The algorithms do not generate any additional message traffic. Instead, load measurement information is opportunistically piggybacked onto application messages. The link load values can be used to initiate process migration and for dynamic flow control. An example of how loads on virtual links may be measured is given.<<ETX>>

An adaptation system for high-performance parallel applications

The authors outline a system that enables the programming of embedded real-time applications that are statically and dynamically adaptable. They describe the need for adaptation support and present the mechanisms that facilitate the programming of adaptations. They present algorithms that have been used in robotics applications to ensure that deadlines are met despite changes in the execution environment.<<ETX>>