Performance and Reliability Enhancement of the Durra Runtime Environment

Abstract

Durra is a language designed to support PMS-level programming . PMS stands for Processor Memory Switch, the name of the highest level in the hierarchy of digital systems. An application or PMS-level program is written in Durra as a set of task descriptions and type declarations that prescribes a way to manage the resources of a heterogeneous machine network. The application describes the tasks to be instantiated and executed as concurrent processes, the types of data to be exchanged by the processes, and the intermediate queues required to store the data as they move from producer to consumer processes. A runtime environment for Durra has been operational for some time. There are two major problems with this initial implementation: it makes no significant attempt to tune the performance of the system, and reliability has not been designed into the system. This report describes a new design for the Durra runtime environment that addresses these two issues. The new runtime environment consists of two major components: a local executive which runs on every processor and is responsible for process and queue management, and a global executive which runs replicated on several processors and is responsible for configuration management and reliability services.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1989
Accession Number
ADA207415

Entities

People

  • Charles Weinstock

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Air Platforms
  • Engineered Resilient Systems
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Computer Programming
  • Computer Programs
  • Computers
  • Configuration Management
  • Consumers
  • Department Of Defense
  • Engineering
  • Environment
  • Executives
  • Fault Tolerance
  • Language
  • Operating Systems
  • Programming Languages
  • Reliability
  • Software Development

Fields of Study

  • Computer science
  • Engineering

Readers

  • Parallel and Distributed Computing.