Repeated issues rebuilding array - multiple drive errors


Recommended Posts

  • 1950X TR
  • Gigabyte X399 Aorus Xtreme
  • 3x10Tb connected to motherboard SATA controller - 1 parity

 

My unraid box has been running for about a year without any issues. Last week it reported errors on all 3 drives - I rebooted and it had disk2 marked as disabled. I removed then re-added the drive to the array, however it would not complete the rebuild due to errors on all 3 drives again.

 

Since then I have:

  1. Updated BIOS
  2. Updated to 6.8.3 (also tried 6.9.0-beta)
  3. Set iommu=pt in kernel boot flags
  4. Replaced all SATA cables
  5. Replaced 2 10Tb drives with new 12Tb drives and copied the parity disk to one of the 10Tb drives (copy was successful but SATA ports reset multiple times for both drives)
  6. Moved drives to different SATA ports on motherboard

 

For each the rebuild will run anywhere from 2hrs to 20hrs before failing with identical failures across all drives.

 

I'm running a rebuild with now with IOMMU disabled in BIOS. Next steps will be replace PSU and potentially MB/CPU.

 

Anything else I am missing here?

unraid-diagnostics-20200405-0730.zip

Link to comment
4 minutes ago, itimpi said:

One non-obvious thing to check is that the HBA is firmly seated in the motherboard slot.    If it has slightly worked its way out due to vibration you can get symptoms of drives unexpectedly failing as a momentary disconnect happens to the motherboard.

I don't have a separate HBA - All the drives are directly connected to the motherboard.

Link to comment
4 minutes ago, johnnie.black said:

Problems with the SATA controller, this is rather common with Ryzem boards, there was a recent report that v6.9-beta fixed the issue, but might not be the same for all boards, BIOS update might also help.

I found a couple of other posts that suggested the same. I was running 6.8.0-rc7 for a while which has the 5.4 kernel, and also tried 6.9.0-beta with 5.5 - Both had the same issue. Also did BIOS update without any changes.

Link to comment

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.