Arch Linux

Excubia

Member

Registered: 2015-08-02

Posts: 29

SSD failure

I have strange things happening. Here is a piece of dmesg :

[ 1276.256188] ata1.00: exception Emask 0x10 SAct 0x1 SErr 0x4040000 action 0xe frozen
[ 1276.256200] ata1.00: irq_stat 0x80000040, connection status changed
[ 1276.256208] ata1: SError: { CommWake DevExch }
[ 1276.256217] ata1.00: failed command: WRITE FPDMA QUEUED
[ 1276.256234] ata1.00: cmd 61/b8:00:f0:2f:6d/00:00:08:00:00/40 tag 0 ncq dma 94208 out
                        res 40/00:7c:b8:8b:3b/00:00:07:00:00/40 Emask 0x10 (ATA bus error)
[ 1276.256242] ata1.00: status: { DRDY }
[ 1276.256254] ata1: hard resetting link
[ 1276.996228] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
[ 1276.996798] ata1.00: unexpected _GTF length (8)
[ 1276.997457] ata1.00: unexpected _GTF length (8)
[ 1276.997511] ata1.00: configured for UDMA/33
[ 1276.997585] ata1: EH complete
[ 1277.299517] ata1.00: exception Emask 0x10 SAct 0x1000000 SErr 0x4040000 action 0xe frozen
[ 1277.299522] ata1.00: irq_stat 0x80000040, connection status changed
[ 1277.299525] ata1: SError: { CommWake DevExch }
[ 1277.299529] ata1.00: failed command: WRITE FPDMA QUEUED
[ 1277.299534] ata1.00: cmd 61/e8:c0:20:ed:7f/00:00:08:00:00/40 tag 24 ncq dma 118784 out
                        res 50/00:00:00:00:00/00:00:00:00:00/a0 Emask 0x10 (ATA bus error)
[ 1277.299537] ata1.00: status: { DRDY }
[ 1277.299541] ata1: hard resetting link
[ 1278.039564] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
[ 1278.040139] ata1.00: unexpected _GTF length (8)
[ 1278.040772] ata1.00: unexpected _GTF length (8)
[ 1278.040823] ata1.00: configured for UDMA/33
[ 1278.040894] ata1: EH complete
[ 1280.049583] ata1.00: exception Emask 0x10 SAct 0x40000 SErr 0x4040000 action 0xe frozen
[ 1280.049595] ata1.00: irq_stat 0x80000040, connection status changed
[ 1280.049604] ata1: SError: { CommWake DevExch }
[ 1280.049613] ata1.00: failed command: READ FPDMA QUEUED
[ 1280.049628] ata1.00: cmd 60/08:90:78:b3:fa/00:00:07:00:00/40 tag 18 ncq dma 4096 in
                        res 50/00:00:00:00:00/00:00:00:00:00/a0 Emask 0x10 (ATA bus error)
[ 1280.049636] ata1.00: status: { DRDY }
[ 1280.049646] ata1: hard resetting link
[ 1280.789592] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
[ 1280.790219] ata1.00: unexpected _GTF length (8)
[ 1280.790896] ata1.00: unexpected _GTF length (8)
[ 1280.790949] ata1.00: configured for UDMA/33
[ 1280.791023] ata1: EH complete
[ 1281.102923] ata1.00: exception Emask 0x10 SAct 0x300 SErr 0x4040000 action 0xe frozen
[ 1281.102936] ata1.00: irq_stat 0x80000040, connection status changed
[ 1281.102944] ata1: SError: { CommWake DevExch }
[ 1281.102951] ata1.00: failed command: WRITE FPDMA QUEUED
[ 1281.102967] ata1.00: cmd 61/08:40:58:03:5b/00:00:08:00:00/40 tag 8 ncq dma 4096 out
                        res 40/00:ac:78:b3:fa/00:00:07:00:00/40 Emask 0x10 (ATA bus error)
[ 1281.102974] ata1.00: status: { DRDY }
[ 1281.102980] ata1.00: failed command: WRITE FPDMA QUEUED
[ 1281.102993] ata1.00: cmd 61/08:48:d8:86:a0/00:00:09:00:00/40 tag 9 ncq dma 4096 out
                        res 40/00:ac:78:b3:fa/00:00:07:00:00/40 Emask 0x10 (ATA bus error)
[ 1281.103000] ata1.00: status: { DRDY }
[ 1281.103011] ata1: hard resetting link
[ 1281.842932] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
[ 1281.843575] ata1.00: unexpected _GTF length (8)
[ 1281.844232] ata1.00: unexpected _GTF length (8)
[ 1281.844302] ata1.00: configured for UDMA/33
[ 1281.844396] ata1: EH complete
[ 1283.179593] ata1.00: exception Emask 0x10 SAct 0x80 SErr 0x4040000 action 0xe frozen
[ 1283.179601] ata1.00: irq_stat 0x80000040, connection status changed
[ 1283.179606] ata1: SError: { CommWake DevExch }
[ 1283.179613] ata1.00: failed command: WRITE FPDMA QUEUED
[ 1283.179622] ata1.00: cmd 61/20:38:60:03:5b/00:00:08:00:00/40 tag 7 ncq dma 16384 out
                        res 40/00:34:08:f1:f3/00:00:09:00:00/40 Emask 0x10 (ATA bus error)
[ 1283.179627] ata1.00: status: { DRDY }
[ 1283.179635] ata1: hard resetting link
[ 1283.919542] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
[ 1283.920040] ata1.00: unexpected _GTF length (8)
[ 1283.920569] ata1.00: unexpected _GTF length (8)
[ 1283.920615] ata1.00: configured for UDMA/33
[ 1283.920674] ata1: EH complete

I use a Macbook Air early 2014, I have just updated the firmwares and I have tried to pass libata.force=1:noncq to the kernel. Nothing has worked so far.

Last edited by Excubia (2017-07-19 07:50:52)

headkase

Member

Registered: 2011-12-06

Posts: 1,977

Re: SSD failure

You should paste your dmesg output in a BBCode code block in your thread.  As it is right now the paste you linked expires in 4 weeks.  Which means after that anyone with a similar problem in the future searching the forum will not be able to view it.  If you edit your first post and paste it in there then it will persist over time.

GenkiSky

Member

From: This account is henceforth dis

Registered: 2017-04-04

Posts: 82

Re: SSD failure

Searching for the first line of your output, I see many people having the same issues, for example https://bbs.archlinux.org/viewtopic.php?id=129401 or https://serverfault.com/questions/74943 … n-0xe-froz . In all links I find, most often people mention bad hardware (motherboard, SATA cables, disk itself, ...) as the issue. I think it would be worth your time to do research on that front and experiment accordingly (recommendation: start with the cheapest but-not-implausible solution first :-).

Last edited by GenkiSky (2017-07-22 01:58:37)

LaurentvdB

Member

Registered: 2017-04-24

Posts: 32

Re: SSD failure

Searching for the first line of your output, I see many people having the same issues, for example https://bbs.archlinux.org/viewtopic.php?id=129401 or https://serverfault.com/questions/74943 … n-0xe-froz . In all links I find, most often people mention bad hardware (motherboard, SATA cables, disk itself, ...) as the issue. I think it would be worth your time to do research on that front and experiment accordingly (recommendation: start with the cheapest but-not-implausible solution first :-).

If it is a hardware issue, you can check the SMART indicators of your SSD using smartctl in the package smartmontools. These indicators can give you an indication about the health of your harddrive and the failure probability.

I hope that it helps.