1st International ICST Conference on Autonomic Computing and Communication Systems

Research Article

Autonomous Performance Control of Distributed Applications in a Heterogeneous Environment

Download50 downloads
  • @INPROCEEDINGS{10.4108/ICST.AUTONOMICS2007.2201,
        author={Keping Chen and Kenneth R. Mayes and John R. Gurd},
        title={Autonomous Performance Control of Distributed Applications in a Heterogeneous Environment},
        proceedings={1st International ICST Conference on Autonomic Computing and Communication Systems},
        publisher={ICST},
        proceedings_a={AUTONOMICS},
        year={2007},
        month={10},
        keywords={performance control adaptivity load balance awareness},
        doi={10.4108/ICST.AUTONOMICS2007.2201}
    }
    
  • Keping Chen
    Kenneth R. Mayes
    John R. Gurd
    Year: 2007
    Autonomous Performance Control of Distributed Applications in a Heterogeneous Environment
    AUTONOMICS
    ICST
    DOI: 10.4108/ICST.AUTONOMICS2007.2201
Keping Chen1,*, Kenneth R. Mayes1,*, John R. Gurd1,*
  • 1: Centre for Novel Computing School of Computer Science, University of Manchester Manchester M13 9PL, United Kingdom
*Contact email: chenk@cs.man.ac.uk, ken@cs.man.ac.uk, jgurd@cs.man.ac.uk

Abstract

A framework is proposed that dynamically adapts to re- source changes in a distributed heterogeneous environment. In this framework, computational tasks are wrapped into autonomous entities which are able to control themselves lo- cally. Global control is provided in a decentralised manner via control units which link with these local entities in hier- archies, monitor them and coordinate their behaviour. With these mechanisms, the framework controls performance of a distributed application in a heterogeneous environment by adjusting load balance and adapting to resource changes. Fault tolerance is provided, being viewed as a special case of performance loss. Mixed strategies are applied, includ- ing global and local control policies, and their benefits are illustrated in terms of scalability and efficiency.