Predicting the Performance of Globus Monitoring and Discovery Service (MDS-2) Queries

  • Authors:
  • Hélène N. Lim Choi Keung;Justin R. D. Dyson;Stephen A. Jarvis;Graham R. Nudd

  • Affiliations:
  • -;-;-;-

  • Venue:
  • GRID '03 Proceedings of the 4th International Workshop on Grid Computing
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Resource discovery and monitoring in a distributed Gridenvironment gives rise to several issues, one of which is theprovision of reliable performance and hence, the quality-of-servicedelivered to Grid users. This performance requirementbrings about the necessity to know how the Monitoringand Discovery Service (MDS) would respond to variousqueries. This paper focuses on the performance ofthe MDS as part of the knowledge needed by a Grid entity,to choose a Grid Index Information Service (GIIS) fordiscovering resources. Several performance metrics are definedand the performance achieved by a GIIS is evaluatedagainst that obtained by a GRIS [15]. Based on the GIISperformance data collected, the values for the performancemetrics are predicted using different algorithms. Thus, pastperformance observations can be used to qualitatively characterisethe future performance of the GIIS, allowing Gridmiddleware built on these services to be more predictable.