hard resetting link exception Emask 0x50 SAct 0x0 SErr 0x4090800 action 0xe frozen
What you server experiences is basically a SATA renegotiation at a lower link speed after some problem communicating with the drives.
These factors can be at work here (ordered by probability)
- very high-latency IOPS operations (eg: caused by SSD controller's garbage collection) resulting in SATA command timeout. Do your drive supports SATA Trim command? If so, try running
fstrim /. Does it change anything? - Bad motherboard/memory: is your memory ECC protected? If not, and if you can, run an extended (2+ hours) memtest86+ test session
- hardware/software drivers incompatibility
- Bad SATA controller: while quite unlikely, you can not completely exclude it
- Bad SATA cables/drives: as all four drives give you problem, this is very unlikely
According to Supermicro Support, the defect lies with board :
Quote:
This board may need ECO 16238 update.