Performance Analysis of the Globus Toolkit Monitoring and Discovery Service, MDS2

TL;DR

This paper quantitatively evaluates the performance of the Globus Toolkit's MDS2 monitoring service, highlighting the benefits of caching and the importance of well-connected sites for optimal performance.

Contribution

It provides a detailed performance analysis of MDS2, offering insights into system limitations and deployment strategies for improved efficiency.

Findings

Caching or prefetching data significantly improves performance.

Primary components should be located at well-connected sites.

Performance bottlenecks identified can guide future optimizations.

Abstract

Monitoring and information services form a key component of a distributed system, or Grid. A quantitative study of such services can aid in understanding the performance limitations, advise in the deployment of the monitoring system, and help evaluate future development work. To this end, we examined the performance of the Globus Toolkit(reg. trdmrk) Monitoring and Discovery Service (MDS2) by instrumenting its main services using NetLogger. Our study shows a strong advantage to caching or prefetching the data, as well as the need to have primary components at well-connected sites.