Navigating the storage iceberg

When I discuss storage with senior IT managers and executives, invariably topping the list of concerns – not surprisingly in this economic environment – is “cost”. There seems to be a sense that ever more precious budget dollars/pounds/euros/or shekels are not being invested as wisely or effectively as they should be. Surprisingly, there is often a lack of hard evidence of this inefficiency and this, in fact, only adds to their discomfort: executives who are called on to approve large storage purchases lack solid information on where the storage that they approve is going and how it’s being consumed. Call it fear of the unknown or perhaps an educated hunch based on experience, I would say that their concerns are well founded.

At its core, the problem with storage stems from the continuing high rates of data growth exacerbated by the fact that our traditionally accepted methods of storing and protecting this data are no longer as effective as they once were.

Picture and iceberg: every byte or GB of data that is created (above the surface) has a multiplier effect in terms of the storage on which it resides (lurking below the surface). If you want to think of this as overhead, you may do so, but to a large extent, much of the overhead is necessary. We have RAID protection that, depending on the method applied, increases storage requirements by 20-100%. We also may make snapshots, additional mirrors, or replicated copies of data that, again, depending on policies and requirements, may increase storage capacity needs several fold.

However, there is also increased consumption based on how we manage storage throughout its lifecycle. This is impacted significantly by not only policies and process, but also by the types of technology deployed in the infrastructure and the tools available to monitor and manage the environment – lack of visibility is a common complaint.

But wait – there’s more! Unlike other aspects of IT, storage is unique in that it is PERSISTANT. Once a byte of data is written, it is highly likely that it will be there forever, carrying all of the overhead just discussed and also multiplying in other ways, such as being backed up and archived.

This all adds up to lots of inefficiency and an underlying cost structure that for most isn’t sustainable. Unfortunately, often the knee-jerk reaction is to focus on technology. Yes, certainly newer technologies like thin provisioning and data deduplication can contribute to improved efficiency. But addressing the problem goes well beyond this: it requires seriously evaluating “business as usual” and applying a multi-pronged approach that includes accurate metrics to improve visibility and form the basis for a plan, a rethinking of allocation and demand management that encourages changed behavior regarding consumption, in combination with the intelligent application of technology. A more piecemeal approach will result in piecemeal results, and won’t ensure successful navigation around the iceberg.

-Jim Damoulakis, GlassHouse CTO

Related posts:

1. VPLEX for Storage Federation: A New Approach to Virtual Storage   EMC’s VPLEX can integrate with VBlocks and leverage VMware,...

Related posts brought to you by Amazon plugin.