You are here

Orchestrating Data-centric Workflows

Adam Barker

When orchestrating data-centric workflows as are commonly found in the sciences, centralised servers can become a bottleneck to the performance of a workflow; output from service invocations are always transferred via a centralised orchestration engine, when they should be passed directly to where they are needed at the next service in the workflow. To address this performance bottleneck, this talk presents a lightweight architecture based on a centralised control flow, distributed data flow model. Our architecture maintains the robustness and simplicity of centralised orchestration, but facilitates choreography by allowing services to exchange data directly with one another, reducing data that needs to be transferred through a centralised server. This talk (in preparation for CCGrid 2008) will introduce the architecture, Web services based API and performance evaluation.

Date and time: 
Wednesday, 6 February, 2008 - 11:00
45 minutes