Performance Analysis of Distributed Applications with ANSAmon
Bernd E. Meyer, M. Heineken, C. Popien · 1995
Distributed computing platforms like DCE or ANSAware offer a number of services to cope with distribution in application programming. With these services some aspects of distribution can be made transparent to programmers. In return programmers partially abandom control over performance of their application. To avoid performance bottlenecks, a distributed applications behaviour needs to be monitored. In this paper we present a distributed monitor called ANSAmon, that we developed for the ANSAware platform. It is realized according to a master-slave architecture and is a distributed application itself. Monitoring experiments can be configured in advance, whereas analysis is done after collecting all events. Global times will be estimated by a new method improving existing ones. Applying ANSAmon we investigated the ANSA REX protocol and the ANSA trader. Important conclusions for the efficient use of ANSAware for distributed applications can be deduced from the results obtained.