Make Big Data Applications More Reliable: Hitless Vsdn Migration To Avoid Tcam Depletion

With network virtualization, an infrastructure provider can create virtual software-defined networks (vSDNs) over a shared substrate network and lease them to service providers (SPs). This enables the SPs to run their Big Data applications in a short time-to-market, flexible and cost-effective way. However, in a dynamic network, both the instances of vSDNs and the traffic in each vSDN can change over time, which would degrade the optimality of the embedding schemes of vSDNs and even cause serious reliability issues. Therefore, in this work, we extend our protocol-oblivious forwarding (POF) based network virtualization hypervisor (NVH) system (i.e., PVX) to realize hitless vSDN migration to avoid ternary content addressable memory (TCAM) depletion. Specifically, we design the PVX system to realize the vSDN migration that is transparent to the controllers of vSDNs and would cause zero or very few packet losses. The proposed PVX is then implemented in a real network testbed, and we conduct experiments to verify its effectiveness.