• Deutsch
  • English

QoS-Aware Execution Environments for Multi-tier Network Services

Classification
Dimension Value
  • Discipline
  • Other
  • Project Working Hours
  • Not Specified
  • Research Study Hybrid Value Creation
    • Funding Institutions
    • National governmental Funding
      • Other
    • Other Funding Institutions
    • National Science Foundation
    Contact Person/s: Dr. Kang Shin

    QoS-Aware Execution Environments for Multi-tier Network Services (ITR/SY)

    Modern, componentized Internet services allow server consolidation  by sharing common service components. Such sharing can potentially reduce the installation cost, space, and energy consumption. However, to date, services  are seldom shared across server applications to avoid possible interference between them. Service providers often run multiple instances of shared services, one for each frontend service. The only benefit gained thus far, from the deployment of multi-tier services is that new services can be composed quickly using existing service components. Since these service components may execute on different machines, each optimally configured for its services, multi-tiered services tend to be more scalable than monolithic counterparts. The proposed research aims to address the shortcoming of current OSs in executing multi-tiered services. We will focus on OS extensions  that correlate and trace service activities across the tiers of a  multi-tiered server farm. We will develop mechanisms for online classification of activities (e.g., premium vs.~basic service classes),  as well as mechanisms that allow system administrators to insulate (performance-wise) different service classes even when the  activities of different service classes may overlap and  share backend services. The same OS mechanisms that are used to manage multi-tiered  services can be used to analyze the interactions between different tiers and the interferences between different service classes.  We will show that a combination of service interaction analysis and service policing minimizes performance invasiveness  between services/applications.  We will also investigate how to improve insulation between services in this environment. We will explore how service implementations may take  advantage of an improved OS infrastructure for multi-tiered.


    This project was described byAdmin Istrator (25. May 2011 - 9:55)
    This project was last edited by Sanja Tumbas (6. July 2012 - 22:08)

    Further information



    This Project is related to the following Organization/s