Flash storage uses electricity and has no mechanical parts. It typically consumes 20% of the power and reads more than one hundred times faster than traditional mechanical hard drives. Data center managers looking for ways to address the energy drain represented by hard drives are examining flash storage as a way to achieve green computing or green data center benchmarks. Businesses with I/O-intensive applications, such as credit card processing systems, have also found flash storage to be efficient and cost-effective. As a result, enterprise storage providers like EMC, chip makers like Samsung and server manufacturers like Sun Microsystems have all entered the flash storage market.
Most flash storage systems are composed of a memory unit and an access controller. The memory unit is used to store data. The access controller manages and controls access to the storage space on the memory unit. Flash storage may consist of a single solid-state drive (SSD) in a laptop or a hybrid hard drive (HHD) that contains both a conventional hard drive and a flash memory module. Data is written onto NAND flash memory, NOR flash memory or a combination of the two.
As interest in flash storage has grown in the market, some industry watchers have also pointed out a frequently overlooked caveat with flash: while its random read access is far superior to traditional hard drives, flash write speeds are lower than their mechanical counterparts, especially in the single-level cell (SLC) devices typically sold to the enterprise. For this reason, and because of flash's relatively limited tolerance for write-erase cycles, users must carefully select and provision data for this medium.