What is virtual sprawl?
Virtualization must be one of the most touted 'silver bullet' solutions of the last ten years. I can't think of any company who hasn't either implemented or considered virtualization. With Server hardware advancing leaps and bounds, and disk space becoming ever cheaper and more plentiful, the ability to partition that space into multiple virtual server environments or 'Virtual Machines' (VMs) has provided many benefits. For data center managers, it makes provisioning new servers a simple task. Extra server capacity can be brought online as and when required, with no additional hardware involved, and a low admin requirement. Once your virtual server image is created, you can have your new army of virtual playgrounds ready and waiting. If a customer needs a server fast - just start one up.
In IT test or development departments it means that developers or tester teams can have access to a new server build at the click of a mouse, which they can then play with, before ditching it and starting up a new one.
So it all sounds amazing, but as we know from past experience, nothing is for nothing. Enter Virtual Sprawl..
Virtual sprawl can be described as the unmanaged spread of VMs without adequate management or control. Or, it’s a bit like my workshop at home, which suffers from the unmanaged spread of tools and other items without any management or control whatsoever.
It usually comes about because of a lack of the correct management processes that are required to track and maintain a VM. Because we can't see a physical VM it's easy to forget about it, unlike a physical server which can be more easily accounted for. Companies jumped on the VM bandwagon without really thinking of the long term implications because virtualization was the answer to so many problems.
What does it all cost?
I think that initially there was a general perception that because VMs are so easy to create and keep on standby they are somehow invisible to cost. If only.
Some time ago I read that the costs associated with virtual servers can be broadly split into four categories. These are infrastructure, management systems, server software, and administration. So you need a physical box on which to host the virtual system, the server software (be that Windows or Unix etc), some admin time and some kind of management - virtual servers need patching too!
However, I would add a fifth category to the above. Each VM that is out there and running is using up energy in the form of the electricity used to power the host server and disks. Just like a real server, a VM needs a slice of the processor time, memory and other hardware services.
It shouldn't all be cost however. If a company decides to implement a virtualization project, the savings can be immediate and quite significant. Depending on the level of virtualization, hundreds or indeed thousands of physical servers can be decomissioned. Once this has been achieved however, it's easy for the rot to set in. Once customers (either internal or external) get to know how easy it is for a VM to be deployed, it creates demand for more and more servers. The number of VMs creeps up and up until you reach a situation where the very cost savings of virtualization have been wiped out and you have a rapidly growing problem on your hands.
Visibility is the Key
In our experiences so far, we have found that NightWatchman Server Edition (NWSE) is a great tool for preparing for virtualization. Using our Useful Work analysis on your physical server population will allow you to identify which servers can be virtualized and/or decommissioned. Armed with this information you can plan your consolidation and virtualization project with precision.
However, it is also the perfect tool for monitoring your VMs once deployed.You can setup regular monitoring and reporting so that you can easily identify any VM which is running but no longer performing it's original task, or is simply under utilised. Consolidation should not be a one-off task, and VMs can and should be included in an ongoing 'server waste-management' plan.
If you suspect that you already have a bad case of virtual sprawl out there, and may have VMs out in the wild that are no longer required, you can also use NWSE to track them down and bring them under control. NWSE can easily highlight VMs which were commissioned in haste (perhaps for a one-off project) and are no longer in use. Or perhaps a whole group of VMs were ordered for a project that is now complete. Once these so called orphaned VMs are identified you can reclaim valuable disk space as well as reducing your energy usage.
Virtualization is a great tool. It's all about doing more with less, and with the right tools to control your VM sprawl you can achieve exactly that.