I'd at least just read all the used blocks on the drive. partclone is the most efficient that comes to mind, because it just copies used sectors. Just redirect to /dev/null.
Or leave the drive on all the time in an enclosure that keeps the nand cool (near room temperature).
Any decent SSD will background rewrite itself over time at an appropriate rate. Detecting that it needs to do so after 2 years in storage seems trickier to get right (no realtime clock) and trickier to test.
I’d be curious to know how quickly the drives in the article “heal” themselves if left plugged in. There’s nothing wrong with the hardware, even if they did lose a few sectors.
If you really want to create a correct protocol, you can accelerate nand aging by sticking them in an oven at an appropriate temperature. (Aging speedup vs temperature curves are available for most nand devices.)
Maybe someone should design and sell a "drivekeeper" that you can plug all your backup SSD's into and it will power them up on a time table and do whatever is necessary to cause them to maintain integrity. Could be something like a Raspberry Pi with a many-port USB hub, or with a PCB with a bunch of connectors the raw drives can plug into. Could maybe even give a warning if a drive is degrading. Possibly it could be a small device with a simple MCU and a battery that you snap directly onto the SSD's connector?
What is the protocol you should use with SSDs that you’re storing? Should you:
- power up the SSD for an instant (or for some minutes?) without needing to read anything?
- or power up the cells where your data resides by reading the files you had created on the SSD?
- or rewrite the cells by reading your files, deleting them, and writing them back to the SSD?