Backblaze published their drive reliability figures. They’ve got a few drives to derive data from, having 300PB of data kind of requires it. The company recently upgraded from 2TB drives from HGST and Western Digital to new Seagate 8TB drives. There was some concern that if these had significantly higher failure rates than the 2TB drive they would prove less cost effective. Afterall, the the HGST drives had a failure rate of just 1.6%.
The Seagate drives so far seem up to the challenge, with an identical 1.6% failure rate of its diminutive predecessor. I’m always a sucker for a good hard drive story. The insane precision needed for spinning disk drives, combined with ever increasing density, should mean that these drives would fail all the time. But instead, spinng disk drive are the most boring part of a system, mostly an afterthought. Good on Backblaze for publishing their figures, it does show that not all vendors are made equal. Notably, Western Digital is responsible for the three highest failure rates, with their 2TB drives hitting 8.2%, ouch!
Of course, as things inevitablly move to flash storage, we’ll see less about drive failure and more about cell endurance for years to come. But until then, let’s give spinning drives some love!
Ars Technica comments:
Cloud backup and storage provider Backblaze has published its latest batch of drive reliability data. The release covers failure information for the 67,642 disks that the company uses to store nearly 300PB of data.
This is actually fewer disks than the company had last quarter, even though the total capacity has gone up. That’s because Backblaze has been upgrading, replacing 2TB disks from HGST and Western Digital with new Seagate 8TB ones. While this upgrade offers size and energy savings, it’s only worthwhile if the failure rate is contained; any more than 2-3 times the failure rate and Backblaze says the migration won’t be worth it.