Scheduling in Cluster Systems

  • Sivarama Dandamudi
Part of the Series in Computer Science book series (SCS)

Abstract

In this chapter, we extend the hierarchical scheduling policy to cluster systems. Cluster systems differ from the shared-memory and distributed-memory systems in several aspects. We present these differences in the first section to provide motivation for the proposed changes to the hierarchical policy for cluster systems. We enhance the hierarchical policy by adding a load-balancing component that can take local load fluctuations into account. Performance of this revised policy is compared with the space- and time-sharing policies used in the last chapter. Our results show that the revised policy handles local load variations and system heterogeneity well and provides better performance than the other two policies.

Keywords

Migration 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 2003

Authors and Affiliations

  • Sivarama Dandamudi
    • 1
  1. 1.Carleton UniversityOttawaCanada

Personalised recommendations