Paper: Container-based Operating System Virtualization: A Scalable, High-performance Alternative to Hypervisors

One stumbling block of the the great march towards virtualization is the relatively poor performance of resource hungry applications like databases. We are told to develop and test using VMs, but deploy without them. Which kind of sucks IMHO. Maybe better virtualization technology can remove this split. This paper talks about a different approach to virtualization called "container-based" virtualization that can reportedly double the performance of traditional hypervisor systems like Xen. It does this by trading isolation for efficiency. Rather than maintaining complete isolation between VMs the container approach shares resources between VMs and thus gives higher performance while still guaranteeing strong fault, resource, and security isolation. It's yet another battle in computing's endless war of creating and destroying abstraction layers. I learned a lot from from this paper because of how it compared and contrasted traditional hypervisor and container based virtualization strategies. Good job.

Comments

[Joris]

Has anyone understood what the difference is between this proposal and linux-vserver or solaris zones?

Also, I think the most compelling reason not to virtualise a database is that it's job is to preserve the data. (fileserver = same principle)
If a data processing node (webserver, numbercruncher, whatever) fails or returns faulty data it's chances are you can still correct it.

But on a service holding data you cannot loose the data nor have it return faulty results.
You want it as reliable as possible, as flawless as possible. You treat the machines with surgeon's gloves, entrust their administration only to the inner circle of senior admins. You sneak by the racks as not to create any vibrations.

Ok, I'm exaggerating, but you definitely don't apply any software or hardware that increases -even ever so slightly- the chance of something going wrong.

Am I being old fasioned?