Whoops! Hewlett Packard Enterprise is telling customers to patch the company’s solid state drives or else the hardware will crash after exactly 32,768 hours of operation. (Or 3 years, 270 days and 8 hours.)
Last week, the company issued the warning about a “firmware defect” in certain server-based SSD models that’ll effectively cause them to expire. “After the SSD failure occurs, neither the SSD nor the data can be recovered,” the bulletin reads. “In addition, SSDs which were put into service at the same time will likely fail nearly simultaneously.”
In other words, the bug risks triggering a systemwide outage at a data center if not patched.
HPE learned of the defect from the SSD’s unnamed manufacturer. According to the bulletin, dozens of different HPE products, including individual SSDs to server models, suffer from the bug.
HPE declined to reveal what’s causing the drives to crash after exactly 32,768 hours of operation. However, the number 32,768 is the maximum negative integer a 16-bit computer can process. Meanwhile, 32,767 is the maximum positive integer. This has sparked speculation the defect has to do with an “integer overflow bug,” where a computer tries to create a numeric value outside the range of available digits only to trigger an error.
In 2015, Boeing 787 planes had to deal with a similar software bug, likely involving a 32-bit integer, that could cause planes to shut down if continously powered over 248 days of operation.
In HPE’s case, the company is urging customers to upgrade the SSD’s firmware to “version HPD8,” and then reboot the server. The firmware patch began rolling out to certain SSD models last week, and will continue into next month.
“We are currently notifying customers of the need to install this update as soon as possible. Helping our customers to remediate this issue is our highest priority,” HPE told PCMag in a statement.