A methodology for evaluating runtime support in network processors

Modern network processor systems require the ability to adapt their processing capabilities at runtime to changes in network traffic. Traditionally, network processor applications have been optimized for a single static workload scenario, but recently several approaches for run-time adaptation have been proposed. Comparing these approaches and developing novel run-time support algorithms is difficult due to the multicore system-on-a-chip nature of network processors. In this paper, we present a model for network processors that can aid in evaluating different run-time support systems. The model considers workload characteristics of applications and network traffic. We use a queuing network abstraction to model different runtime systems. We illustrate the effectiveness of this model by comparing the performance of two existing workload adaptation algorithms.