First parity errors on v6

[tucansam]

6.0-rc5

 

Have been running it for a while now.  1 Aug's automatic parity test resulted in 5 parity errors found.  I know this is minimal, but its the first time I've had errors on this system.

 

Syslog entries that piqued my interest:

 

--

 

Jul 27 12:32:27 ffs2 kernel: ata7.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen

Jul 27 12:32:27 ffs2 kernel: ata7.00: failed command: IDENTIFY DEVICE

Jul 27 12:32:27 ffs2 kernel: ata7.00: cmd ec/00:01:00:00:00/00:00:00:00:00/00 tag 19 pio 512 in

Jul 27 12:32:27 ffs2 kernel:        res 40/00:00:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)

Jul 27 12:32:27 ffs2 kernel: ata7.00: status: { DRDY }

Jul 27 12:32:27 ffs2 kernel: ata7: hard resetting link

Jul 27 12:32:27 ffs2 kernel: ata7: SATA link up 3.0 Gbps (SStatus 123 SControl 300)

Jul 27 12:32:27 ffs2 kernel: ata7.00: configured for UDMA/133

Jul 27 12:32:27 ffs2 kernel: ata7: EH complete

Jul 27 12:49:52 ffs2 kernel: mdcmd (446): spindown 3

Jul 27 13:44:23 ffs2 kernel: mdcmd (447): spindown 3

Jul 27 14:06:51 ffs2 kernel: ata7.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen

Jul 27 14:06:51 ffs2 kernel: ata7.00: failed command: IDENTIFY DEVICE

Jul 27 14:06:51 ffs2 kernel: ata7.00: cmd ec/00:01:00:00:00/00:00:00:00:00/00 tag 24 pio 512 in

Jul 27 14:06:51 ffs2 kernel:        res 40/00:01:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)

Jul 27 14:06:51 ffs2 kernel: ata7.00: status: { DRDY }

Jul 27 14:06:51 ffs2 kernel: ata7: hard resetting link

Jul 27 14:06:51 ffs2 kernel: ata7: SATA link up 3.0 Gbps (SStatus 123 SControl 300)

Jul 27 14:06:51 ffs2 kernel: ata7.00: configured for UDMA/133

Jul 27 14:06:51 ffs2 kernel: ata7: EH complete

 

 

Aug  1 00:00:01 ffs2 kernel: mdcmd (578): check NOCORRECT

Aug  1 00:00:01 ffs2 kernel:

Aug  1 00:00:01 ffs2 kernel: md: recovery thread woken up ...

Aug  1 00:00:01 ffs2 kernel: md: recovery thread checking parity...

Aug  1 00:00:01 ffs2 kernel: md: using 2048k window, over a total of 2930266532 blocks.

Aug  1 02:11:41 ffs2 kernel: md: parity incorrect, sector=1565565768

Aug  1 02:11:41 ffs2 kernel: md: parity incorrect, sector=1565565776

Aug  1 02:11:41 ffs2 kernel: md: parity incorrect, sector=1565565784

Aug  1 02:11:41 ffs2 kernel: md: parity incorrect, sector=1565565792

Aug  1 02:11:41 ffs2 kernel: md: parity incorrect, sector=1565565800

Aug  1 05:00:48 ffs2 kernel: ata9.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen

Aug  1 05:00:48 ffs2 kernel: ata9.00: failed command: IDENTIFY DEVICE

Aug  1 05:00:48 ffs2 kernel: ata9.00: cmd ec/00:01:00:00:00/00:00:00:00:00/00 tag 22 pio 512 in

Aug  1 05:00:48 ffs2 kernel:        res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)

Aug  1 05:00:48 ffs2 kernel: ata9.00: status: { DRDY }

Aug  1 05:00:48 ffs2 kernel: ata9: hard resetting link

Aug  1 05:00:48 ffs2 kernel: ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300)

Aug  1 05:00:48 ffs2 kernel: ata9.00: configured for UDMA/133

Aug  1 05:00:48 ffs2 kernel: ata9: EH complete

Aug  1 06:52:14 ffs2 kernel: mdcmd (579): spindown 2

Aug  1 06:52:15 ffs2 kernel: mdcmd (580): spindown 4

Aug  1 06:52:15 ffs2 kernel: mdcmd (581): spindown 5

Aug  1 06:52:15 ffs2 kernel: mdcmd (582): spindown 7

Aug  1 06:58:37 ffs2 kernel: ata7.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen

Aug  1 06:58:37 ffs2 kernel: ata7.00: failed command: IDENTIFY DEVICE

Aug  1 06:58:37 ffs2 kernel: ata7.00: cmd ec/00:01:00:00:00/00:00:00:00:00/00 tag 6 pio 512 in

Aug  1 06:58:37 ffs2 kernel:        res 40/00:ff:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)

Aug  1 06:58:37 ffs2 kernel: ata7.00: status: { DRDY }

Aug  1 06:58:37 ffs2 kernel: ata7: hard resetting link

Aug  1 06:58:37 ffs2 kernel: ata7: SATA link up 3.0 Gbps (SStatus 123 SControl 300)

Aug  1 06:58:37 ffs2 kernel: ata7.00: configured for UDMA/133

Aug  1 06:58:37 ffs2 kernel: ata7: EH complete

Aug  1 10:04:54 ffs2 kernel: md: sync done. time=36292sec

Aug  1 10:04:54 ffs2 kernel: md: recovery thread sync completion status: 0

 

 

Aug  2 11:35:26 ffs2 kernel: ata7.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen

Aug  2 11:35:26 ffs2 kernel: ata7.00: failed command: SMART

Aug  2 11:35:26 ffs2 kernel: ata7.00: cmd b0/d0:01:00:4f:c2/00:00:00:00:00/00 tag 1 pio 512 in

Aug  2 11:35:26 ffs2 kernel:        res 40/00:01:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)

Aug  2 11:35:26 ffs2 kernel: ata7.00: status: { DRDY }

Aug  2 11:35:26 ffs2 kernel: ata7: hard resetting link

Aug  2 11:35:26 ffs2 kernel: ata7: SATA link up 3.0 Gbps (SStatus 123 SControl 300)

Aug  2 11:35:26 ffs2 kernel: ata7.00: configured for UDMA/133

Aug  2 11:35:26 ffs2 kernel: ata7: EH complete

 

--

 

Not sure what to make of this.  Advice welcome. 

 

Thanks.

[trurl]

You shouldn't be running such an old rc , especially since the stable branch is already on 6.1.9

 

Also, the notion that only 5 parity errors is minimal is completely wrong. If you have any parity errors at all it can corrupt a data disk rebuild.

 

Syslog snippets are seldom sufficient. Always post complete diagnostics zip.

 

Was this a correcting parity check? If so, you should run another to see if the parity errors have all been corrected.

[John_M]

The controllers seem to be losing communication with the disks and resetting the links. I'd power down and check the relevant SATA cables before doing another parity check.

[tucansam]

You shouldn't be running such an old rc , especially since the stable branch is already on 6.1.9

 

Also, the notion that only 5 parity errors is minimal is completely wrong. If you have any parity errors at all it can corrupt a data disk rebuild.

 

Syslog snippets are seldom sufficient. Always post complete diagnostics zip.

 

Was this a correcting parity check? If so, you should run another to see if the parity errors have all been corrected.

 

 

Literally the entire rest of the syslog was spindown entries.

[tucansam]

The controllers seem to be losing communication with the disks and resetting the links. I'd power down and check the relevant SATA cables before doing another parity check.

 

I pulled the server apart last month to dispose of dust bunnies, I probably bumped something, good call.

 

Thanks to all.