Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

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?

share|improve this question
up vote 1 down vote accepted

There's a whole giant part of ESX that helps you with this, VM reservations and shares. Set a VM's reservations to the resource levels you NEED that VM to have as a bare minimum and set its share level to be higher than other less important VMs. I wouldn't go messing around with processor affinity just yet, these should sort you out. Feel free to ask again once you're up and running with more detailed questions.

share|improve this answer
Thanks for the pointers. I'm going with these controls first and we'll branch out further if necessary. – Rick Reynolds Sep 22 '09 at 22:39

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.