Backblaze is back again, this time with updated hard drive statistics and failure rates for all of 2016. Backblaze’s quarterly reports on HDD failure rates and statistics are the best data set we have for measuring drive reliability and performance, so let’s take a look at the full year and see who the winners and losers are.
Backblaze only includes hard drive models in its report if it has at least 45 drives of that type, and it currently has 72,100 hard drives in operation. The slideshow below explains and steps through each of Backblaze’s charts, with additional commentary and information. Each slide can be clicked to open a full-size version in a new window.
Backblaze has explained before that it can tolerate a relatively high failure rate before it starts avoiding drives altogether, but the company has been known to take that step (it stopped using a specific type of Seagate drive at one point due to unacceptably high failure rates). Current Seagate drives have been much better and the company’s 8TB drives are showing an excellent annualized failure rate.
Next, we’ve got something interesting — drive failure rates plotted against drive capacity.
The giant peak in 3TB drive failures was driven by the Seagate ST3000DM001, with its 26.72% failure rate. Backblaze actually took the unusual step of yanking the drives after they proved unreliable. With those drives retired, the 3GB failure rate falls back to normal.
One interesting bit of information in this graph is that drive failure rates don’t really shift much over time. The shifts we do see are as likely to be caused by Backblaze’s perpetual rotation between various manufacturers as old drives are retired and new models become available. Higher capacity drives aren’t failing at statistically different rates than older, smaller drives, implying that buyers don’t need to worry that bigger drives are more prone to failure.
The usual grain of salt
As always, Backblaze’s data sets should be taken as a representative sample of how drives perform in this specific workload. Backblaze’s buying practices prioritize low cost drives over any other type, and they don’t buy the enterprise drives that WD, Seagate, and other manufacturers position specifically for these kinds of deployments. Whether or not this has any impact on consumer drive failure rates isn’t known — HDD manufacturers advertise their enterprise hardware as having gone through additional validation and being designed specifically for high-vibration environments, but there are few studies on whether or not these claims result in meaningfully better performance or reliability.
Backblaze’s operating environment has little in common with a consumer desktop or laptop, and may not cleanly match the failure rates we would see in these products. The company readily acknowledges these limitations, but continues to provide its data on the grounds that having some information about real-world failure rates and how long hard drives live for is better than having none at all. We agree. Readers often ask which hard drive brands are the most reliable, but this information is extremely difficult to come by. Most studies of real-world failure rates don’t name brands or manufacturers, which limits their real-world applicability.