If you could have all flash performance at 80% of the cost of an all-flash solution, would you be interested? From a financial point of view, it is hard to argue.
It is pretty well documented that for most applications, less than 5-10% of the data across a volume is active at any point in time. Given this, it does not make sense to pay all flash prices to store your inactive data. Granted, there are applications that are active across the entire LBA range of a volume, or that cannot tolerate any unpredictable latency. For these applications, by all means, an all-flash solution is the right choice.
For the majority of us, a hybrid solution is the optimal choice. Keep in mind that not all hybrid solutions are created equal. For optimal performance, your hybrid solution should have the following characteristics:
- File pinning because there are applications for which you want to guarantee full flash performance for all IO
- Real time data promotion to performance storage because the solution should react to dynamic requirements, not yesterday’s activity
- Full automation because your time is too valuable to constantly manage storage
- Unrestricted fast tier capacities because you need the ability to size your storage to your unique needs
- Visibility into your storage behavior because you need information to guarantee your storage is optimized