Smartd "CHECK POWER STATUS spins up disk (0x81 -> 0xff)" despite constant activity

The setup:

5 servers running Linux Mint with approximately 12-14 HDD each, mining arweave. Arweave is a storage based crypto which never stops reading a minimum of 15 MB/s per drive. Storage access is constant.

Yet in journalctl, every time smartd fires off every half hour, 2-3 of the 14 drives in the system produce these log messages:

May 16 13:43:28 Excalibur smartd[3699]: Device: /dev/sdb [SAT], CHECK POWER STATUS spins up disk (0x81 -> 0xff)
May 16 13:43:33 Excalibur smartd[3699]: Device: /dev/sdc [SAT], CHECK POWER STATUS spins up disk (0x81 -> 0xff)
May 16 13:43:38 Excalibur smartd[3699]: Device: /dev/sdg [SAT], CHECK POWER STATUS spins up disk (0x81 -> 0xff)
```

Which 3 or 4 drives out of my 14 HDD on the example system will get called out as the disk being spun up seems entirely random.

None of these drives should ever be spun down or show a device status as such. Not just because of the constant reads every single second, but also because I have “spindown_time” set in /etc/hdparm.conf set to 240 (which is 20 minutes), and also because I have this udev rule: `ACTION==“add”, SUBSYSTEM==“scsi_host”, KERNEL==“host*”, ATTR{link_power_management_policy}=“max_performance”` that should be turning off any power management in these links.

I know that if I remove “-n standby” (the command that should tell smartd to not poll a drive in standby so it doesn’t get spun up) from my smartd parameter I should stop getting this message. But before I do this, I really want to know the cause of these messages, and if my drives are somehow getting put into undesirable power states despite the constant activity and settings.

Anyone have any idea?