• DocumentCode
    3406626
  • Title

    A middleware implementation and performance evaluation of the SNS scheme for network surveillance

  • Author

    Kim, K. H Kane ; Liu, Juqiang

  • Author_Institution
    DREAM Lab., California Univ., Irvine, CA, USA
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    43
  • Lastpage
    50
  • Abstract
    Network surveillance (NS), which is basically a (partially or fully) decentralized mode of detecting the faulty/repaired status of distributed computing (DC) components, is a major part of real-time (RT) fault-tolerant DC. One NS technique which is broadly applicable and amenable to rigorous quantitative analyses of fault coverage is the supervisor-based network surveillance (SNS) scheme for use in point-to-point network-based systems. Recently, we have been studying an approach to implementing the SNS scheme within a middleware model, named the TMO (time-triggered message-triggered object) Support Middleware (TMOSM) which is layered above a commercial off-the-shelf (COTS) operating system such as Windows 2000 and functions as a reliable RT execution engine for RT DC applications. The DC applications supported by the TMOSM are those designed by use of the TMO programming scheme. The implementation structure as well as the observed performance of a prototype implementation are discussed
  • Keywords
    client-server systems; computer network management; computer network reliability; distributed object management; fault diagnosis; performance evaluation; real-time systems; surveillance; SNS scheme; commercial off-the-shelf operating systems; decentralized detection mode; fault coverage; faulty status; implementation structure; performance evaluation; point-to-point network-based systems; programming scheme; prototype implementation; real-time execution engine; real-time fault-tolerant distributed computing components; repaired status; rigorous quantitative analyses; supervisor-based network surveillance; time-triggered message-triggered object support middleware; Broadcasting; Computer networks; Distributed computing; Engines; Fault detection; Fault tolerance; Local area networks; Middleware; Prototypes; Surveillance;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Object-Oriented Real-Time Dependable Systems, 2001. Proceedings. Sixth International Workshop on
  • Conference_Location
    Rome
  • ISSN
    1530-1443
  • Print_ISBN
    0-7695-1068-X
  • Type

    conf

  • DOI
    10.1109/WORDS.2001.945112
  • Filename
    945112