Home > Technology > Flash Life Support
With a lack of standardization, write/erase cycle endurance for solid-state storage is specified in many ways by the different flash vendors. Some vendors use the physical flash block level to specify the product's endurance, while others refer to logical block level, or even drive level. In addition, endurance is also related to data retention can be specified higher if the data retention specification is lower. It is therefore better to compare all the components that affect the endurance calculation and evaluate those instead.
Flash endurance is based on what NAND flash technology is used (SLC vs. MLC) and what the capabilities are of the flash controller in terms of error correction, wear leveling algorithm, bad block management, etc.
The individual blocks in a NAND flash device are limited in the number of Program/Erase Cycles they can sustain before the probability of errors rise to unacceptable levels. It is therefore extremely important that all blocks within a flash chip are aging in the same manner. If one area gets written to frequently, while another gets never touched, the lifetime of the entire flash is impacted.
To overcome this limitation, a flash file system needs to be implemented to make sure that with any new write operation, the youngest block is used. STEC's implemented wear leveling scheme spreads flash media usage evenly across all pages, thereby maximizing flash lifetime.
The implemented Error Correction algorithm in a flash controller has a direct influence on the overall flash endurance number. When a certain flash block has reached its write/erase cycle limit, it will show a higher probability of errors. By implementing a powerful ECC mechanism that can detect and correct these errors with our advanced ECC protocols that minimize byte errors per flash page (512 bytes), STEC's flash controller can extend the life of a flash block far beyond its original specification, thereby extending the overall lifespan of the solid state drive.
When implementing flash management algorithms that include a strong wear leveling and Error Correction Mechanism, there is also a need for the management algorithm to monitor and maintain bad blocks within the NAND device. Many NAND-based products maintain tables of known bad blocks, while STEC's management algorithm not only maintains the existing bad block table, but also monitors the device for new bad blocks during use. STEC can then replace the new bad blocks and update all necessary aspects of the data contained in spare blocks that are reserved for use. This practice further enhances the overall SSD lifespan.
Flash manufacturers specify a limit on how many write/erase cycles can be performed on a given page before the signs of wear-out become obvious and the probability of errors rise to unacceptable levels. Today's generation of Single Level Cell NAND Flash devices are guaranteed for 100,000 Program/Erase cycles per Erase Block with 1-bit ECC. Multi Level Cell NAND flash devices are offered with only 10,000 cycles.
|
