Runtime Resource Allocation Model over Network Processors

Abstract

Delivering high performance when several virtual nodes share the same physical resources requires finding the optimal resource allocation between them. In the context of Software Defined Network (SDN) and Network Virtualization, data plane requires the design of a new and more flexible flow packet processing. Virtual nodes involves several packet processing functions such as search operations in different data structures, processing the packets by modifying their respective contents and buffering them. Each packet processing requires a set of shared resources. If there is a conflict for a given resources, resource reassignment strategy is needed to ensure the continuity of the processing and solve resource congestion in accordance with the available hardware resources. In this paper, we propose a resource allocation strategy to share fairly the network processor resources. It is based on network calculus model and game theory algorithms. This strategy maps dynamically the suitable resources according to virtual nodes processing. In our implementation, we focus on packet processing tasks in regard to OpenFlow forwarding model within several processors to reassign resources.