Most presentations one hears at industry trade shows and conferences have to do, fundamentally, with Capacity Allocation Efficiency (CAE). CAE seeks to answer a straightforward question: Given a storage capacity of x petabytes or y exabytes, how will we divvy up space to workload data in a way that reduces the likelihood of a catastrophic “disk full” error?
Essentially, from a CAE perspective, efficiency involves balancing the volume of bits across physical storage repositories in a way that does not leave one container nearly full while another has mostly unused space. The reason is simple. As the volume of data grows and the capacity of media (whether disk or flash) increases, a lot of data – with many users — can find its way into a single repository. In so doing, access to the data can be impaired (a lot of access requests across a few bus connections can introduce latency). This, in turn, shows up in slower application performance, whether the workload is a database or a virtual machine.