Microsoft plans for use of partially damaged hard drives in datacenters as new standards emerge

Kareem Anderson

Many of us have experienced the gut-wrenching despair of a hard drive failure, be it on an external hard drive meant to back up or supplement a portion of centralized storage or losing everything on a laptop or desktop drive a few years beyond its prime. Traditionally, once a hard drive fails, it’s over, and it then becomes shopping time for a better, larger, more “reliable” replacement.

But what if a drive failure wasn’t the end?

Microsoft and other storage providers are looking into implementing new standards that could give hard-drives “run-flat” type technologies, ensuring that while a crash may limit a drives useful storage capabilities, safeguards can help maintain its integrity.

According to a report from the TechRepublic, “the idea is called logical depopulating and goes by “depop” in a system command set. It is being proposed by industry standards committees and would allow more efficient maintenance schedules in large-scale data centers because a hard drive could keep most of its capacity available until its turn to be replaced comes along.”

While Microsoft and others are looking to standardize the technology, some have already begun shipping devices with a proprietary implementation. Western Digital and Seagate Technology have equipped several of their hard drive offerings with offline logical depop technologies. Thanks to newer enterprise drives being developed with sealed segments, full-scale driver failures are becoming more infrequent. Now, host drives can identify a failed portion of a drive and efficiently work to put the rest of the drive together enabling access to the remainder of store data while segmenting a corrupted portion.

For Microsoft’s part, the company would need to begin a process of changing the way Windows files systems currently operate to help transition the process. Given over 30 years of legacy cruft embedded in the current Windows file system, Joe Breher, a storage architect from Longmont, Colorado believes it could take some time before that becomes a reality.

However, the Microsoft Azure team’s agility in the storage industry is planning to implement offline logical depop technology shortly.

You end up with so much capacity offline, especially at the end-of-life of a cluster, that you lose a lot of value,” said Aaron Ogus, manager of the Microsoft Azure storage hardware team, in Redmond, Washington. “What is likely to happen with depop is this. In the first generation for Microsoft Azure storage, we will do offline depop. In a future iteration, we will work with the file system team.”

Berh and the Microsoft Azure team are working to shorten the standards process for logical depopulating down to a 12-18-months that could see implementation into Azure some 6 to 12 months afterward.

Clearly, there are a lot of moving parts, and the reality of run-flat-like drives is still far on the horizon for businesses and consumers experiencing drive failures currently. However, if Microsoft and other storage companies can push this technology into a standard practice, the longevity of hybrid solutions gets extended and with that consumers and businesses hold on to more options for storage.