January 22, 2014, 10:32 AM — Cloud service provider Backblaze has been busily releasing data over the past several months from a massive study of more than 27,000 hard drives it uses in its data centers.
Last November, the company released the first batch of data showing that 22% of more than 25,000 consumer-grade hard drives in its rack-mounted servers die in their first four years.
Today, the Backblaze released what is arguably the most important information yet: which vendor's hard drive products last the longest. The result are based on a study that lasted three years.
At the end of 2013, the company had 27,134 consumer-grade drives spinning in Storage Pods. A storage pod is an array of RAIDed disks made up by either 2.5 or 3.5-in, hard drives used to storage customer data. Each Pod stores up to 180TB in a 4U rack-mounted configuration.
The company filled the Storage Pods with drives from Seagate, Hitachi and Western Digital; it also used drives from Toshiba and Samsung, but their numbers were so small as to be statistically insignificant. For example, the company used 12,765 Seagate drives, 12,956 Hitachi drives and 2,838 Western Digital drives. It only used 58 drives from Toshiba and 18 from Samsung.
The results from three years of use were revealing: Western Digital's drives lasted an average of 2.5 years, while Hitachi's and Seagate's lasted 2 and 1.4 years, respectively. Even so, some of the individual Hitachi models topped the reliability charts.
Annual failure rate based on manufacturer and capacity (source: Backblaze)
"Hitachi does really well. There is an initial die-off of Western Digital drives, and then they are nice and stable. The Seagate drives start strong, but die off at a consistently higher rate, with a burst of deaths near the 20-month mark," Backblaze wrote in its official blog. "Having said that, you'll notice that even after 3 years, by far most of the drives are still operating."
It's also important to note that Backblaze is using the drives in an environment that sees far more input and output activity than the average desktop or laptop computer would produce; the drives are continuously in use in what is an enterprise-class environment.
Backblaze measured reliability by looking at the annual failure rate, which is the average number of failures you can expect running one drive for a year. A failure is when a drive in a pod must be replaced, the company said.
The company included specific drive models and their capacities in their results. It listed 15 different drive models from Western Digital, Seagate and Hitachi.
Topping the list for reliability was Hitachi's 3TB Deskstar 7K3000 (HDS723030ALA640) with a 0.9% failure rate and an average lifetime of about 2.1 years.
The second highest in reliability was also a Hitachi drive, the Deskstar 5K3000 (HDS5C3030ALA630); it also had a .09% failure rate with an average lifetime of 1.7 years.
The drive model with the highest failure rate was Seagate's 1.5TB Barracuda Green (ST1500DL003). It averaged only a 0.8-year lifespan, which gave it an annual failure rate of 120%.
Drive survival rate over 36 months of use (source: Backblaze)
Not all Seagate drives performed so poorly.
Backblaze said it has been happy with Seagate's Barracuda LP 1.5TB drives.
"We've been running them for a long time - their average age is pushing 4 years. Their overall failure rate [9.9%] isn't great, but it's not terrible either," the company stated. "The bigger Seagate drives have continued the tradition of the 1.5TB drives: they're solid workhorses, but there is a constant attrition as they wear out."
Western Digital, while performing the best on average, also suffered hits on some of specific drives as well.
"The drives that just don't work in our environment are Western Digital Green 3TB drives and Seagate LP (low power) 2TB drives. Both of these drives start accumulating errors as soon as they are put into production. We think this is related to vibration," Backblaze stated.
The company said it will continue to measure the performance of its drives and release data periodically on those metrics.
Lucas Mearian covers storage, disaster recovery and business continuity, financial services infrastructure and health care IT for Computerworld. Follow Lucas on Twitter at @lucasmearian, or subscribe to Lucas's RSS feed . His email address is email@example.com.
Read more about data storage in Computerworld's Data Storage Topic Center.