Cloud Web interface should allow overcommit on CPU

[Neil Wilson]

Currently the default installation of UEC restricts the number of VMs based on the lower of memory and core numbers retrieved from the node controllers.

There should be an option in the visual interface to allow a cluster to overcommit on CPU. Ordinarily when you're providing VMs on a cluster memory is the only restricting factor you require - kvm does a good job of sharing out processor power. CPU cores should be the number of cores available to the instance rather than dedicated to it.

The workaround at the moment appears to be increasing MAX_CPUS to a large value in the cluster controller.

[Neil Soman (neilsoman)]

You can already set this via the MAX_CORES value in eucalyptus.conf on individual nodes. It is unclear whether using a blanket value across all nodes via the front end config is a good idea. We provide a finer level control at the individual node level and I don't think this will be changing for Karmic.

[Thierry Carrez (ttx)]

Following upstream rationale on this.

[Dustin Kirkland  (kirkland)]

I'm actually going to convert this to a question.

I suspect this will come up again.

:-Dustin

[Dustin Kirkland  (kirkland)]

Neil Soman wrote 5 hours ago: #1

You can already set this via the MAX_CORES value in eucalyptus.conf on individual nodes. It is unclear whether using a blanket value across all nodes via the front end config is a good idea. We provide a finer level control at the individual node level and I don't think this will be changing for Karmic.

[Etienne Goyer (etienne-goyer-outlands)]

Neil Soman wrote:
> You can already set this via the MAX_CORES value in eucalyptus.conf on
> individual nodes. It is unclear whether using a blanket value across all
> nodes via the front end config is a good idea. We provide a finer level
> control at the individual node level and I don't think this will be
> changing for Karmic.

The problem is that you have to go and manually change MAX_CORES on all
the node controllers. Moreover, you will need to restart the NC
service, which could bring downtime. Being able to overcommit resource
at the cluster level would greatly simplify the process.

Apparently, this is important to corporate users, as I have had that
question before. I think the reasoning is sound; there is no reason to
arbitrarily limit the number of instances.

I am certainly not expecting such a thing to be implemented for karmic,
but if it could get somewhere on Eucalyptus, that would be great.

--
Etienne Goyer
Technical Account Manager - Canonical Ltd
Ubuntu Certified Instructor

 ~= Ubuntu: Linux for Human Beings =~