Last week in was in a number of business development meetings when the question came up, "Can real-time compression work with SSD?" I thought the question was a bit odd because I would have assumed it was obvious that real-time compression would work with any primary storage, including SSD but it turns out that the question was just a validation question on the road to a brilliant solution stack for SSD. The two big issues with SSD are cost and concern around number of writes to these devices before failure (or MTBF in traditional terms).
When it comes to cost, the average cost per terabyte for SSD is still 8x the cost of standard FC disk. It is for this reason that companies such as EMC are pulling the proverbial wool over the customers eyes by telling customers that the formula they need to consider when it comes to storage costs is no longer about dollars per gigabyte but dollars per gigabyte per disk I/O. And while this is an important and useful formula, the overall cost is still critical end users. By performing compression before the data gets to the SSD you can, at a minimum, reduce the cost by 2x and in some cases 10x (depending upon your compression ratio) and if compression is being performed in real-time, the storage performance can even increase (imagine that, increasing your SSD performance and cutting the cost in half!)
The next issue with SSD is the issue with write failures over time. Weather this is a myth or an issue that is blown out of proportion it still comes up with customers. The two characteristics that are important to customers when buying storage are performance (noted above as a function of dollars per I/O) and availability. If there is the slightest chance that SSD will loose data, I don't care how fast it is, I can't use it. Now, if real-time compression sits in front of SSD drives, and does the compression before the data is stored on disk then the disk I/O is cut by 50% or more which extends the life of the disk. Less I/O means less less reads and writes from the SSD which in turn means greater long term value of the SSD.
I keep saying 'real-time' compression here. It is important to keep in mind that if you don't do real-time compression then you do the basic industry compression which will negatively impact the MTBF of an SSD. The reason: because with 'traditional compression' it is post process meaning it compressed the data once the data is stored. This means that not only is there a full write for every file, there is a full read for every file and then a subsequent, albeit smaller write for the compressed file. This is a lot more I/O that would be seen in non-compressed environments.
The bottom line, if you want to save money and extend the life of your solid state disk drives, you need to be doing real-time compression.