We have a set of servers running VMware ESXi 4 and run a set of Linux machines on them (it's a VMed rocks cluster, actually). One of the nodes on a host is a high-priority server that should always get preferential treatment in terms of processing power if the VMware host machine gets loaded.
What's the best way to setup something like this? The servers have 8 cores. Is there a way to effectively tie one of the cores to the important VM, so that other VMs can't use it? Or is this kind of effect better achieved by reserving MHz under resource allocation? Or is this what scheduling affinity is best used for?