Big Parity® from StreamScale leads the industry in RAID reliability and processing speed, eliminating data loss and corruption due to disk failure, service errors, silent data corruption, and unrecoverable read errors. 30X faster than competitive RAID systems, Big Parity is the only product that provides advanced Verified Erasure Coding® which enable up to 127 parity drives to keep data safe and accurate during long data analysis cycles or rebuilds.

Drive Reliability

Rely on published MTBF or AFR numbers for disk drives at your own peril. These theoretical numbers are calculated in a lab environment and don't include real world service data. To believe the MTBF numbers would mean most drives would not fail even in 100 years! Do you really believe that?

In real life, annual disk failure rates are on average 2-4% and can go as high as 13% according to a study conducted by Carnegie Mellon University and similar results reported by Google researchers. And consider that drive manufacturers only estimate and never update MTBF numbers to reflect measured reliability. Just take a look at the Seagate bricked drives or the IBM “DeathStar” drives, both of which had reported failures at much higher rates. In both cases, the manufacturers never changed their MTBF numbers, even though both drives had serious reliability problems reported around the world. What does this mean about MTBF? You better hope that your system doesn't already have the next "brick" or "DeathStar" drive in it. But, when it comes to data protection, hope is not a strategy.

The truth is, all disk drives are very fragile devices. They depend on careful packaging and handling or they can be permanently damaged and their warranties voided. They are also sensitive to even small changes in their environment. If you don’t carefully control their mechanical mounting, temperature, or power levels, they will malfunction. In fact, they are so sensitive that even the sound of your voice can cause them to generate errors, as shown in this video. Drives fail so often that the sound is quite familiar to those with experience, and is called “the click of death”.

And don’t forget that many drives fail when deployed in a customer site, but when retested in the manufacturer’s “lab”, they work fine (no trouble found). Unfortunately, most businesses don’t have the luxury of establishing a carefully controlled laboratory for their storage system. Customer failure rates are many times higher than published specs, and the failure rate for some drive models are astronomically higher. Who will ship the next “brick” or “DeathStar”? No one will know until after they ship, maybe to your business.

Traditional RAID6 arrays are limited to only 2 drive protection, and no protection from Silent Data Corruption, especially during reconstruction cycles. Instead, they amplify SDC, and record corrupted data even on healthy drives, with no possibility of recovery. Is that good enough to protect your business assets?

Contact us now to get more information on how your organization can take advantage of Big Parity to protect your data from drive failures. Join the discussion on our Forum page and tell us about your real world story about storage reliability.

Drive relaibility needs Big Parity