The hardware is an Intel Xeon server with two ST120FP0021 - Seagate 600 Pro 120GB SSDs configured as a RAID 1 array. The /boot, /root and / partition are mounted on these disks.<br />
<br />
The system is running with all updates applied to date.<br />
<br />
After a few minutes or sometimes a few hours, the logs start showing intermittent HSM violation errors and eventually, the system crashes.<br />
<br />
I disabled NCQ on both disks and the frequency of errors reduced, but it still occurs and the system eventually crashes.<br />
<br />
I am unable to access the system locally or remotely after the crash and need to do a hard reset to reboot.
↧
