Loading...

Design and Implementation of Resource Allocation Mechanisms in Fault-tolerant Distributed Real-time Systems

Nabavi, Sahebeh | 2013

493 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 44760 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Miremadi, Ghassem
  7. Abstract:
  8. One of the most important characteristics of real-time systems is executing tasks before their specified deadlines. The tasks’ execution may require several resources like processor, I/O ports, and data structures. Some of these resources may be shared between several tasks and their availability is important in executing tasks before the deadlines. Allocating shared resources which are used in mutually exclusive manner often encounteres some problems such as priority inversion and deadlock. Resource access protocols are used to minimize or eliminate these problems. The effect of using these protocols issupporting tasks’ execution before their deadlines. To meet deadlines is of decisive importance in safety-critical distributed real-time systems which need high reliability. The aim of this thesis is to minimizethe above problems and to increase the reliability with considering shared resource faults; this is achieved by two contributions: 1) a novel resource access protocol is proposed to solve the above mentioned problems.This protocol eliminates the problems of well-known protocolslikehigh run time overhead. The protocol is offered for periodic tasks with hard deadlines which are scheduled with RM scheduling algorithm, 2)A fault-tolerant method for public resource access protocols is proposed. In this method, before each resource allocation to a task, a checkpoint is taken from the task. In this way, when a transient fault is occurred in the resource, the execution of the task is repeated before resource allocation. The method can tolerate a transient resource fault in the execution of each task. The experimental results show that the proposed fault-tolerant method incurs about 10% time overhead
  9. Keywords:
  10. Resources Allocation ; Safety-Critical Real-Time System ; Fault Tolerance ; Distributed System ; Real Time System

 Digital Object List

 Bookmark

No TOC