Not sure what to believe, but I like having my ZFS NAS running so it can regularly run scrubs and check the data. FWIW, I’ve run my 4 drive system for 10 years with 2 drive failures in that time, but they were not enterprise grade drives (WD Green).
Theres a difference between spinning a drive up/down once or twice a day and spinning it down every 15 minutes or less.
Also WD Green drives are not recommended for NAS usage. I know in the past they used to park the read/write head every few seconds or so which is fine if data is being accessed infrequently but continuously however a server this can result in continuous wear which leads to premature failure.
I’m running a 3 disk ZFS mirror of 8-10yr old greens and are yet to have an issues.
Which leads to another strategy which is to swap the primary and the backup after 5 years to get a good 10y out of the two NAS.
Keep them running.
Why?:
* The read/write heads experience literally next to no wear while they are floating above the platters. They physically land onto shelves or onto landing zones on the platters themselves when turned off; landing and takeoff are by far the most wear the heads will suffer.
* Following on the above, in the worst case the read/write heads might be torn off during takeoff due to stiction.
* Bearings will last longer; they might also seize up if left stationary for too long. Likewise the drive motor.
* The rush of current when turning on is an electrical stressor, no matter how minimal.
The only reasons to turn your hard drives off are to save power, reduce noise, or transport them.
All HDD failures I've ever seen in person (5 across 3 decades), were bearing failures, in machine that were almost always on with drives spun up. It's difficult to know for sure without proper A-B comparisons, but I've never seen a bearing failure in a machine where drives were spun down automatically.
It also seems intuitive that for mechanical bearings the longer they are spun up the greater the wear and the greater the chance of failure.
Counterpoints for each: Heads don't suffer wear when parking. The armature does.
If the platters are not spinning fast enough, or the air density is too low: the heads will crash into the sides of the platters.
The main wear on platter bearings is vibration, it takes an extremely long time for the lube to "gum up." If its still a thing at all. I suspect it used to happen because they were petroleum distilate lubes. So, shorter chains would evaporate/sublimate leaving longer more viscous chains. Or straight polymerize.
With fully synthetic PAO oils, and other options they won't do that anymore.
What inrush? They're polyphase steppers. The only reason for inrush is that the engineers didn't think it'd affect lifetime.
Counter: turn your drives off, thebsaved power of 8 drives being off half the day easily totals $80 a year- enough to replace all but the highest capacities.
One reason some of my drives get powered down 99+% of the time is that its a way to guard against the whole network getting cryptolockered. i have a weekly backup run by a script that powers up a pair of raid1 usb drives, does and incremental no-delete backup, then unmounts and powers them back down again. Even in a busy week theyre rarely running for more than an hour or two. I'd have to get unlucky enough to not have the powerup script detect being cryptolockered (it checks md5 hashes of a few "canary files") and powering up the bav=ckup drives anyway. I figure that's a worthwhile reason to spin them down weekly...
if you really want to protect yourself from crypto lock attacks, which seems odd for an individual to be concerned about (nobody extorts individuals for a few hundred dollars to get the keys, they extort businesses for many thousands of dollars) then you need write once media like MDISC or WORM tapes.
In the case of the IronWolf NAS drives in my home server, that's 600,000.
I spin the drives down after 20 minutes of no activity, which I feel is a good balance between having them be too thrashy and saving energy. After 3 years I'm at about 60,000 load unload cycles.
OTOH, when the NAS spins up a single disk again, I haven't notice any additional load. Presumably, the read operation just waits until the disk is ready.
I was under the impression that this was, in fact, known to reduce drive longevity! It is done anyway in order to save power, but the reliability tradeoff is known.
No idea where I read that though, I thought it was "common knowledge" so maybe I'm wrong.
If so then yes, keeping them spinning may help improve lifespan by reducing frequent disk jerk. This is really only applicable when you're at a pretty consistent high load and you're trying to prevent your disks from spinning up and down every few minutes or something.
For a homelab, you're probably wasting way more money in electricity than you are saving in disk maintenance by leaving your disks spin.
Does this include some kind of built-in hash/checksum system to record e.g. md5 sums of each file and periodically test them? I have a couple of big drives for family media I'd love to protect with a bit more assurance than "the drive did not fail".