The data storage industry has steadily progressed, based on a model of delivering increasing device capacity with a decreasing price per unit. How often have you heard someone state how cheap storage has become? Since the early ‘90s, the price per gigabyte of disk storage has fallen 25 to 40 percent annually. Most of the dialogue centers around the price and capacity of storage, but the third key element—performance—is less often discussed yet it’s increasingly important.
Both disk drive and tape cartridge capacities are growing faster than their corresponding data rates and are projected to continue this trend through 2012. But some key questions today are:
- How long can capacities increase without corresponding increases in performance?
- What are the real limits of storage?
- Are the real data storage limits technological or practical?
- Why do most storage vendors drive capacity advancements so much more aggressively than performance improvements?
Areal densities are expected to grow 40 to 60 percent annually and now indicate a clear path to nearly 5TB or more per drive by 2013 at the latest. However, disk drive performance capabilities haven’t kept pace with the growth in disk capacities. Disk drive performance is improving less than 10 percent annually. Raw disk drive performance specifications are normally measured in total random I/Os per second and can surpass 100 I/Os per second per disk actuator; the average access time (average seek, latency, and data transfer) is about 10 to 5ms per I/O on many newer drives.
Continual increases in capacity, without corresponding performance improvements at the drive level, create a performance imbalance that’s defined by the ratio called disk access density. Access density is the ratio of performance, measured in I/Os per second, to the capacity of the drive, usually measured in gigabytes (access density = I/Os per second per gigabyte [see Figure 1]).