This work addresses an apparently simple but elusive problem that arises when doing high speed networking on Virtual Machines. When a VM and its peer (usually the hypervisor) process packets at different rates, the work required for synchronization (interrupts and“kicks”) may reduce throughput well below the slowest of the two parties. The problem is not peculiar to VMs: I/O on magnetic tapes and rotating disks has similar issues. What is challenging with VM networking is the timescale at which interactions may occur: down to tens or hundreds of nanoseconds,