VIRTUALIZATION TECHNOLOGY FOR TCPIP OFFLOAD ENGINE

Network IO virtualization plays an important role in cloud computing. This paper addresses the system-wide virtualization issues of TCPIP Offload Engine (TOE) and presents the architectural designs. We identify three critical factors that affect the performance of TOE IO virtualization architectures, quality of service (QoS), and virtual machine monitor (VMM) scheduler. In our device emulation based TOE, the VMM manages the socket connections in the TOE directly and thus can eliminate packet copy and demultiplexing overheads as appeared in the virtualization of a layer 2 network card. To further reduce hypervisor intervention, the direct IO access architecture provides the per VM-based physical control interface that helps removing most of the VMM interventions. The direct IO access architecture out-performs the device emulation architecture as large as 30%, or achieves 80% of the native 10 Giga bits TOE system. To continue serving the TOE commands for a VM, no matter the VM is idle or switched out by the VMM, we decouple the TOE IO command dispatcher from the VMM scheduler. We found that a VMM scheduler with preemptive IO scheduling and a programmable IO command dispatcher with deficit weighted round robin (DWRR) policy are able to ensure service fairness and at the same time maximize the TOE utilization