Since the day before yesterday (first 7.2.6 as of today 7.3.0), I’ve been seeing the error below more and more frequently. At first, it happened every few hours. Now, it’s happening every few minutes.

I have a total of 6 SATA SSDs in my setup. However, since I only have 4 SATA ports on the motherboard, I had to install an ASM1166 expansion card in an NVMe slot, to which two of the SSDs are connected.

Unfortunately, the error doesn’t specify exactly which drive is causing the issue. I’d like to ask for some help with this.

May 15 14:15:11 PurpleGravity kernel: ata8.00: exception Emask 0x10 SAct 0x400000 SErr 0x400100 action 0x6 frozen
May 15 14:15:11 PurpleGravity kernel: ata8.00: irq_stat 0x08000000, interface fatal error
May 15 14:15:11 PurpleGravity kernel: ata8: SError: { UnrecovData Handshk }
May 15 14:15:11 PurpleGravity kernel: ata8.00: failed command: WRITE FPDMA QUEUED
May 15 14:15:11 PurpleGravity kernel: ata8.00: cmd 61/18:b0:68:4b:9a/00:00:89:01:00/40 tag 22 ncq dma 12288 out
May 15 14:15:11 PurpleGravity kernel: res 40/00:01:00:00:00/00:00:00:00:00/00 Emask 0x10 (ATA bus error)
May 15 14:15:11 PurpleGravity kernel: ata8.00: status: { DRDY }
May 15 14:15:11 PurpleGravity kernel: ata8: hard resetting link
May 15 14:15:11 PurpleGravity kernel: ata8: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
May 15 14:15:11 PurpleGravity kernel: ata8.00: supports DRM functions and may not be fully accessible
May 15 14:15:11 PurpleGravity kernel: ata8.00: supports DRM functions and may not be fully accessible
May 15 14:15:11 PurpleGravity kernel: ata8.00: configured for UDMA/133
May 15 14:15:11 PurpleGravity kernel: ahci 0000:00:17.0: port does not support device sleep
May 15 14:15:11 PurpleGravity kernel: ata8: EH complete
May 15 14:15:11 PurpleGravity kernel: ata8.00: Enabling discard_zeroes_data

purplegravity-diagnostics-20260515-1435.zip

Edited May 17May 17 by purplehexagon
removed diagnostics for privacy reasons, solved

Check/replace both cables and retest.

I've swapped the cable for Main 4 (sdf) bc following logs leads me that sdf is responsible, isn' it?

Even though today's log is dated 2026-05-16, it was also "ata8.00" yesterday and the day before.

May 16 13:38:16 PurpleGravity kernel: scsi 7:0:0:0: Direct-Access     ATA      Samsung SSD 870  3B6Q PQ: 0 ANSI: 5
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: Attached scsi generic sg5 type 0
May 16 13:38:16 PurpleGravity kernel: ata8.00: Enabling discard_zeroes_data
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: [sdf] 7814037168 512-byte logical blocks: (4.00 TB/3.64 TiB)
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: [sdf] Write Protect is off
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: [sdf] Mode Sense: 00 3a 00 00
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: [sdf] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
May 16 13:38:16 PurpleGravity kernel: sd 7:0:0:0: [sdf] Preferred minimum I/O size 512 bytes

I'll monitor the log today, and if the same errors occur again, I'll check the cables on the ASM1166 controller.

Edited May 16May 16 by purplehexagon
forgot one sentence

I have checked my log over the last 20 hours, and no errors have occurred. So replacing the cable with a new one seems to have fixed the problem.

Thanks @JorgeB for your help!