Analytical architecture-based performability evaluation of real-time software systems

  • Authors:

  • Faeze Eshragh;Mehdi Kargahi

  • Affiliations:

  • Dependable and Real-Time Systems (DRTS) Research Lab., School of Electrical and Computer Engineering, College of Engineering, University of Tehran, P.O. Box 14399-57131, Tehran, Iran;Dependable and Real-Time Systems (DRTS) Research Lab., School of Electrical and Computer Engineering, College of Engineering, University of Tehran, P.O. Box 14399-57131, Tehran, Iran

  • Venue:
  • Journal of Systems and Software
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Real-time systems are usually employed in dynamic and harsh environments. Real-time software, as one important part of such systems, potentially suffers from two problems: unpredictability in the timing behavior which affects the software performance, and logical faults which affect the software reliability. The former problem is mitigated by improving the software algorithm, architecture, and code. The latter problem is also relieved via software redundancy methods, even though these methods may adversely affect the software performance and architectural complexity. Despite these problems, it is expected to have a guaranteed service level in real-time systems, which the service is defined as the successful completion of the software mission within its deadline. In this paper, we propose two architecture-based analytical methods for simultaneous performance and reliability (performability) evaluation of real-time component-based software: one is accurate and the other is approximate. The accurate method is sound and precise but more complex in the computations, while the approximate method is easy-to-follow with reasonable amounts of computations. Examples of different configurations have been presented to show how well the latter method approximates the former one. Some performability sensitivity analyses with respect to the software component properties have also been done for better depiction of the importance of employing the proposed analytical methods in finding and eliminating the software performability bottlenecks.