More and more network devices and chips commonly apply multi-core architectures to meet increasingly performance demands. But the lack of efficient program level parallelism and workload allocation in the packet processing system greatly limits the utilization of multi-core architectures. In this paper, we propose a parallel packet processing runtime system and explore an affinity-based packet scheduler with the goal of raising load balancing and decreasing cache miss. We can use the system that handles the allocation of processing tasks to simplify the implementation of new applications. The experiment results show task distributor and scheduler can achieve a better compromise between load balancing and cache affinity in the parallel packet processing system.
展开▼
