CircusTalk: an orchestration service for distributed multimedia

Distributed multimedia applications consist of a mixture of elements scattered at different locations on a network. Each element on the network has different transmission needs and each link of the network has different transmission characteristics. Just as an orchestra conductor must match the characteristics of instruments to the performance skills of the musicians-then orchestrate the piece according to their location in the orchestra and the acoustic properties of the hall. So too, a multimedia orchestration service must take A/V elements, match them to the A/V servers with appropriate responsiveness, and distribute the elements to appropriate locations on the network. To do this, we have created an orchestration service that integrates and centralizes the orchestration task thereby relieving the individual elements from being aware of how they are being composited to form a combined application and hopefully also leading to globally optimal and balanced networks. Distributed multimedia applications consist of a mixture of elements distributed over a network. For example, in figure 1, we show a collaborative media-space [3] where two scientists are conducting a joint transcontinental experiment. One scientist has a high-resolution SEM microscope, the other provides the NMR scanner. Both are producing real-time video which they are also processing in real-time. The results of the image processing is being used to drive a real-time simulation which is providing a parallel representation of the results. They will be sharing the video, but having separate simulators and renderers so that they can view different aspects of the simulation. In order to build this system, processing tasks (e.g. image processing) will have to be matched to appropriate compute servers, input/output data flows will have to be characterized, and appropriate network connections established. However, this binding cannot be static. Loading changes on the compute servers and changes in traffic flow patterns on the underlying ATM network must be constantly monitored. In response to load changes, alternative virtual connections or alternative compute servers may have to be rescheduled to maintain the QoS guarantees. From this specific example, we can create a general statement of the multimedia orchestration problem. Distributed multimedia applications consist of a set of elements. Elements can act as either