Monitoring of Grid scientific workflows
Scientific Programming - Large-Scale Programming Tools and Environments
An instrumentation infrastructure for grid workflow applications
ODBASE'06/OTM'06 Proceedings of the 2006 Confederated international conference on On the Move to Meaningful Internet Systems: CoopIS, DOA, GADA, and ODBASE - Volume Part II
Hi-index | 0.00 |
Legacy applications are still heavily used in Grid systems. In modern service-oriented Grid environments such applications are adapt- ed to work as services. Monitoring of applications is often necessary for various purposes, such as debugging, performance analysis, fault-tolerance, etc. In this paper we present a framework for monitoring of legacy applications wrapped as services. We adapt the OCM-G system for monitoring of distributed legacy applications (such as MPI) to work as part of a broader service-oriented monitoring infrastructure GEMINI. We address monitoring and instrumentation at both service-level and legacy-level. Our instrumentation is fine-grained, i.e. we support instrumentation and monitoring at the level of individual code regions.