Hey guys,

 

I'm in the process of bringing my first Unraid array online, and I'm seeing several I/O errors in the sys log, and as a beginner, I'm not sure what they mean. I've formatted this post in sections so that it's (hopefully) easier to digest. Diags are attached to this post, as well as the syslog output that's concerning me.

 

THE ISSUE:

I'm not sure what the issues in my syslog mean or how to fix them, and I have a feeling that they are impacting my read/write speeds significantly, especially since my parity sync is running so slow (ranges from KB/s to max 50 MB/s) . Extensive googling and a long conversation with ChatGPT were not helpful, as I don't think I was asking the right questions.

 

CONTEXT:

This is my first array. When I checked the sys logs to make sure everything was normal, I saw the lines printed in the snippet at the bottom of this post over and over again. ata 7 is my parity one parity drive, or at least, the one I want to be my parity drive. I had an SDD in a pool and four HDDs in an array. Another HDD is physically connected but not in the array as it was slowing my parity sync down to KB/s. I have Plex installed on Docker, but Docker is currently disabled. No other applications are installed. This is my first time starting up an array.

 

DIAGNOSTICS:

I've replaced all of my SATA cables with new cables and switched all of the HDDs from being plugged into the motherboard SATA slots to a PCI card with SATA slots. This produced no change, and the errors persisted (albeit with a different ata#). SMART tests give that all of my drives are healthy. I have a feeling this is an issue at the hardware level.

 

SYSLOG OUTPUT:

Feb 16 22:55:47 WolflikeNAS kernel: ata7.00: failed to IDENTIFY (I/O error, err_mask=0x4)
Feb 16 22:55:47 WolflikeNAS kernel: ata7.00: revalidation failed (errno=-5)
Feb 16 22:55:47 WolflikeNAS kernel: ata7: hard resetting link
Feb 16 22:55:49 WolflikeNAS kernel: ata7: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
Feb 16 22:55:49 WolflikeNAS kernel: ata7.00: configured for UDMA/33
Feb 16 22:55:49 WolflikeNAS kernel: ata7: EH complete
Feb 16 22:55:54 WolflikeNAS kernel: ata7.00: exception Emask 0x10 SAct 0x3f0 SErr 0x400100 action 0x6
Feb 16 22:55:54 WolflikeNAS kernel: ata7.00: irq_stat 0x08000000
Feb 16 22:55:54 WolflikeNAS kernel: ata7: SError: { UnrecovData Handshk }
Feb 16 22:55:54 WolflikeNAS kernel: ata7.00: failed command: WRITE FPDMA QUEUED
Feb 16 22:55:54 WolflikeNAS kernel: ata7.00: cmd 61/40:20:60:ed:4b/05:00:0b:00:00/40 tag 4 ncq dma 688128 out
Feb 16 22:55:54 WolflikeNAS kernel:         res 40/00:01:01:4f:c2/00:00:00:00:00/00 Emask 0x10 (ATA bus error)
Feb 16 22:55:54 WolflikeNAS kernel: ata7.00: status: { DRDY }

 

argentNASdiags.zip

Replace cables for parity or swap them with a different disk and see where the issue follows.

Thanks for the response! I did try swapping cables and different SATA ports, issue not resolved. It followed the drive. The issue is that I don't know what the errors I'm getting actually mean in the context of my server.

If the errors follow the drive, it suggests a drive problem.