Hpe hub banner.png

HPE advises users to patch SSDs to prevent crashes after precisely 32,768 hours of operation

The issue impacts 20 SSD models in total

Hewlett Packard Enterprise (HPE) has advised users to immediately patch their ProLiant server SSDs to prevent them from permanently crashing after precisely 32,768 hours of operation.

In a warning issued last week, the company said that a "firmware defect" in some SAS SSDs (serial-attached SCSI solid-state drives) discovered some time back is causing those devices to fail after exactly three years, 270 days and eight hours of operation.

These SAS SSDs are currently used in multiple server and storage products, such as the HPE ProLiant, Apollo, D6xxx, MSA, and StoreVirtual 4335.

"After the SSD failure occurs, neither the SSD nor the data can be recovered," HPE stated in its advisory.

"In addition, SSDs which were put into service at the same time will likely fail nearly simultaneously," it added.

The PC maker said that users who keep data backups on different drives will be able to recover their data, but data stored on HPE SSD will be unrecoverable.

In total, 20 drives, including server models to individual SSDs, suffer from the issue. These models come with a firmware version prior to HPD8. Upgrading the firmware to version HPD8 will fix the issues, according to the company.

So far, HPE has released a fix for only eight drives. For remaining 12 drives, HPE plans to release a fix in the second week of December.

The company warned that neglecting to update the firmware will result in drive failure and data loss, and it will require "restoration of data from backup in non-fault tolerance, such as RAID 0 and in fault tolerance RAID mode if more drives fail than what is supported by the fault tolerance RAID mode logical drive."

Users can check the uptime of their installed drives using the Smart Storage Administrator (SSA) software.

According to HPE, it was notified about the bug by another SSD manufacturer, whose name it did not reveal.

While the company didn't say anything about what is causing the SSDs to crash after 32,768 hours of operation, some experts speculated that it could be happening due to "integer overflow" with a computer attempting to create a numeric value outside the range of available digits.

HPE advises users to patch SSDs to prevent crashes after precisely 32,768 hours of operation

The issue impacts 20 SSD models in total

Mergers

EU to decide fate of $14bn HPE-Juniper Networks merger next month

Law

US court clears Mike Lynch of fraud charges

Threats and Risks

Microsoft: Russian hackers are targeting other companies