The simple dollar per gigabyte metric no longer applies in evaluating storage solutions now that embedded systems computing has migrated to mobile devices and cloud storage. Developers have started to use a more sophisticated review process based on their specific application and its related data-type usage model. This has caused several SSD application classes to emerge. These classes are referred to as client, enterprise, data center and embedded SSDs.
So what characteristics differentiate SSDs built for each application class?
This paper discusses the general industry trends that SSDs need to meet to be viable solutions for the four main enterprise, data center, client, and industrial/embedded markets. It will also introduce a new, more definitive application class for industrial/embedded SSDs called infrastructure SSDs that are evaluated to satisfy the unique storage requirements of equipment used to connect the Internet of Things. The information presented will not deal so much with how an SSD is built or the components inside, but rather the more important desired metrics that must be optimized for each application class. The ultimate purpose is that thorough knowledge of usage models can drastically reduce costs and enhance storage design efficiency by selecting the right SSD based on the key operating parameters required for a specific application.