Raid5 assemble after dual sata port failure

Hi,

While on vacation I had one SATA port/cable fail, and then four hours later a second one fail. After fixing/moving the SATA ports, I can reboot and all drives seem to be OK now, but when assembled it won't recognize the filesystem. After futzing around with assemble options like --force and disk order I couldn't get it to work.

Appreciate if someone can provide pointers on how to proceed. Here's the latest state of the array. My log shows that /dev/sdc1 failed first and I'm using mdadm v2.5.6 on Ubuntu Linux.

Thanks much,
Chris

mdadm -Av /dev/md0
mdadm: looking for devices for /dev/md0
mdadm: /dev/sda1 is identified as a member of /dev/md0, slot 0.
mdadm: /dev/sdb1 is identified as a member of /dev/md0, slot 1.
mdadm: /dev/sdc1 is identified as a member of /dev/md0, slot 3.
mdadm: /dev/sdd1 is identified as a member of /dev/md0, slot 2.
mdadm: added /dev/sdb1 to /dev/md0 as 1
mdadm: added /dev/sdd1 to /dev/md0 as 2
mdadm: added /dev/sdc1 to /dev/md0 as 3
mdadm: added /dev/sda1 to /dev/md0 as 0
mdadm: /dev/md0 has been started with 3 drives (out of 4).

mdadm -E /dev/sd[a-d]1
/dev/sda1:

         Magic : a92b4efc
       Version : 00.90.03
          UUID : bc74c21c:9655c1c6:ba6cc37a:df870496
 Creation Time : Sun Nov  5 14:25:01 2006
    Raid Level : raid5
   Device Size : 488383936 (465.76 GiB 500.11 GB)
    Array Size : 1465151808 (1397.28 GiB 1500.32 GB)

Raid Devices : 4
Total Devices : 3
Preferred Minor : 0

Update Time : Wed Nov 7 12:02:50 2007
State : clean
Active Devices : 3
Working Devices : 3
Failed Devices : 1
Spare Devices : 0
Checksum : 401c33e0 - correct
Events : 0.4880374

Layout : left-symmetric
Chunk Size : 64K

Number Major Minor RaidDevice State
this 0 254 0 0 active sync /dev/mapper/sda1

  0     0     254        0        0      active sync   /dev/mapper/sda1
  1     1     254        1        1      active sync   /dev/mapper/sdb1
  2     2     254        2        2      active sync   /dev/mapper/sdd1
  3     3       0        0        3      faulty removed
/dev/sdb1:
         Magic : a92b4efc
       Version : 00.90.03
          UUID : bc74c21c:9655c1c6:ba6cc37a:df870496
 Creation Time : Sun Nov  5 14:25:01 2006
    Raid Level : raid5
   Device Size : 488383936 (465.76 GiB 500.11 GB)
    Array Size : 1465151808 (1397.28 GiB 1500.32 GB)

Raid Devices : 4
Total Devices : 3
Preferred Minor : 0

Update Time : Wed Nov 7 12:02:50 2007
State : clean
Active Devices : 3
Working Devices : 3
Failed Devices : 1
Spare Devices : 0
Checksum : 401c33e3 - correct
Events : 0.4880374

Layout : left-symmetric
Chunk Size : 64K

Number Major Minor RaidDevice State
this 1 254 1 1 active sync /dev/mapper/sdb1

  0     0     254        0        0      active sync   /dev/mapper/sda1
  1     1     254        1        1      active sync   /dev/mapper/sdb1
  2     2     254        2        2      active sync   /dev/mapper/sdd1
  3     3       0        0        3      faulty removed
/dev/sdc1:
         Magic : a92b4efc
       Version : 00.90.03
          UUID : bc74c21c:9655c1c6:ba6cc37a:df870496
 Creation Time : Sun Nov  5 14:25:01 2006
    Raid Level : raid5
   Device Size : 488383936 (465.76 GiB 500.11 GB)
    Array Size : 1465151808 (1397.28 GiB 1500.32 GB)

Raid Devices : 4
Total Devices : 4
Preferred Minor : 0

Update Time : Mon Nov 5 13:31:00 2007
State : active
Active Devices : 4
Working Devices : 4
Failed Devices : 0
Spare Devices : 0
Checksum : 3fced5a3 - correct
Events : 0.4857597

Layout : left-symmetric
Chunk Size : 64K

Number Major Minor RaidDevice State
this 3 254 3 3 active sync /dev/mapper/sdc1

  0     0     254        0        0      active sync   /dev/mapper/sda1
  1     1     254        1        1      active sync   /dev/mapper/sdb1
  2     2     254        2        2      active sync   /dev/mapper/sdd1
  3     3     254        3        3      active sync   /dev/mapper/sdc1
/dev/sdd1:
         Magic : a92b4efc
       Version : 00.90.03
          UUID : bc74c21c:9655c1c6:ba6cc37a:df870496
 Creation Time : Sun Nov  5 14:25:01 2006
    Raid Level : raid5
   Device Size : 488383936 (465.76 GiB 500.11 GB)
    Array Size : 1465151808 (1397.28 GiB 1500.32 GB)

Raid Devices : 4
Total Devices : 3
Preferred Minor : 0

Update Time : Wed Nov 7 12:02:50 2007
State : clean
Active Devices : 3
Working Devices : 3
Failed Devices : 1
Spare Devices : 0
Checksum : 401c33e6 - correct
Events : 0.4880374

Layout : left-symmetric
Chunk Size : 64K

Number Major Minor RaidDevice State
this 2 254 2 2 active sync /dev/mapper/sdd1

  0     0     254        0        0      active sync   /dev/mapper/sda1
  1     1     254        1        1      active sync   /dev/mapper/sdb1
  2     2     254        2        2      active sync   /dev/mapper/sdd1
  3     3       0        0        3      faulty removed

Hi

That's unusual - if the array comes back then you should be OK. In general if two devices fail then there is a real data loss risk. However if the drives are good and there was just a cable glitch, then unless you're unlucky it's usually fsck fixable.

I see
mdadm: /dev/md0 has been started with 3 drives (out of 4).

which means it's now up and running.

And:
sda1 Events : 0.4880374
sdb1 Events : 0.4880374
sdc1 Events : 0.4857597
sdd1 Events : 0.4880374

so sdc1 is way out of date... we'll add/resync that when everything else is working.

but:

Let me check... what commands did you use? Just 'assemble' - which doesn't care about disk order - or did you try to re-'create' the array - which does care about disk order and leads us down a different path...
err, scratch that:

OK, it was created a year ago... so you did use assemble.

It is slightly odd to see that the drive order is:
/dev/mapper/sda1
/dev/mapper/sdb1
/dev/mapper/sdd1
/dev/mapper/sdc1
Usually people just create them in order.

Have you done any fsck's that involve a write?

What filesystem are you running? What does your 'fsck -n' (readonly) report?

Also, please report the results of:
cat /proc/mdadm
mdadm -D /dev/md0
cat /etc/mdadm.conf

David

Thanks David.

I've had cable/port failures in the past and after re-adding the drive, the order changed - I'm not sure why, but I noticed it sometime ago but don't remember the exact order.

My initial attempt to assemble, it came up with only two drives in the array. Then I tried assembling with --force and that brought up 3 of the drives. At that point I thought I was good, so I tried mount /dev/md0 and it failed. Would that have written to the disk? I'm using XFS.

After that, I tried assembling with different drive orders on the command line, i.e. mdadm -Av --force /dev/md0 /dev/sda1, ... thinking that the order might not be right.

At the moment I can't access the machine, but I'll try fsck -n and send you the other info later this evening.

Many thanks,
Chris

Hi David,

I ran xfs_check and get this:
ERROR: The filesystem has valuable metadata changes in a log which needs to be replayed. Mount the filesystem to replay the log, and unmount it before re-running xfs_check. If you are unable to mount the filesystem, then use the xfs_repair -L option to destroy the log and attempt a repair. Note that destroying the log may cause corruption -- please attempt a mount of the filesystem before doing this.

After mounting (which fails) and re-running xfs_check it gives the same message.

The array info details are below and seems it is running correctly ?? I interpret the message above as actually a good sign - seems that xfs_check sees the filesystem but the log file and maybe the most currently written data is corrupted or will be lost. But I'd like to hear some advice/guidance before doing anything permanent with xfs_repair. I also would like to confirm somehow that the array is in the right order, etc. Appreciate your feedback.

Thks,
Chris

--------------------
cat /etc/mdadm/mdadm.conf
DEVICE /dev/sda1 /dev/sdb1 /dev/sdc1 /dev/sdd1
ARRAY /dev/md0 level=raid5 num-devices=4 UUID=bc74c21c:9655c1c6:ba6cc37a:df870496 MAILADDR root

cat /proc/mdstat
Personalities : [raid6] [raid5] [raid4]
md0 : active raid5 sda1[0] sdd1[2] sdb1[1]

     1465151808 blocks level 5, 64k chunk, algorithm 2 [4/3] [UUU_]

unused devices: <none>

mdadm -D /dev/md0
/dev/md0:

       Version : 00.90.03

Creation Time : Sun Nov 5 14:25:01 2006
Raid Level : raid5
Array Size : 1465151808 (1397.28 GiB 1500.32 GB)
Device Size : 488383936 (465.76 GiB 500.11 GB)
Raid Devices : 4
Total Devices : 3
Preferred Minor : 0
Persistence : Superblock is persistent

Update Time : Fri Nov 9 16:26:31 2007
State : clean, degraded
Active Devices : 3
Working Devices : 3
Failed Devices : 0
Spare Devices : 0

Layout : left-symmetric
Chunk Size : 64K

UUID : bc74c21c:9655c1c6:ba6cc37a:df870496
Events : 0.4880384

Number Major Minor RaidDevice State

      0       8        1        0      active sync   /dev/sda1
      1       8       17        1      active sync   /dev/sdb1
      2       8       49        2      active sync   /dev/sdd1
      3       0        0        3      removed

Ok - it looks like the raid array is up. There will have been an event count mismatch which is why you needed --force. This may well have caused some (hopefully minor) corruption.

FWIW, xfs_check is almost never worth running :) (It runs out of memory easily). xfs_repair -n is much better.

What does the end of dmesg say after trying to mount the fs?

Also try:
xfs_repair -n -L

I think you then have 2 options:
* xfs_repair -L
This may well lose data that was being written as the drives crashed.
* contact the xfs mailing list

David

Hi,

Thanks for the pointer on xfs_repair -n , it actually tells me something (some listed below) but I'm not sure what it means but there seems to be a lot of data loss. One complication is I see an error message in ata6, so I moved the disks around thinking it was a flaky sata port, but I see the error again on ata4 so it seems to follow the disk. But it happens exactly at the same time during xfs_repair sequence, so I don't think it is a flaky disk. I'll go to the xfs mailing list on this.

Is there a way to be sure the disk order is right? What I mean is when using --force does is try to figure out the right order based on best possible recognition of something there, or does it just take the existing disk order and assemble them? I want to be sure that this is not way out of wack since I'm seeing so much from xfs_repair. Also since I've been moving the disks around, I want to be sure I have the right order.

Is there a way to try restoring using the other disk?

Thks,
Chris

- creating 4 worker thread(s)
Phase 1 - find and verify superblock...
- reporting progress in intervals of 15 minutes
Phase 2 - using internal log
- scan filesystem freespace and inode maps...
bad on-disk superblock 2 - inconsistent filesystem geometry in realtime filesystem component primary/secondary superblock 2 conflict - AG superblock geometry info conflicts with filesystem geometry would reset bad sb for ag 2
bad uncorrected agheader 2, skipping ag...
bad on-disk superblock 24 - bad magic number
primary/secondary superblock 24 conflict - AG superblock geometry info conflicts with filesystem geometry bad flags field in superblock 24
bad shared version number in superblock 24
bad inode alignment field in superblock 24
bad stripe unit/width fields in superblock 24
bad log/data device sector size fields in superblock 24
bad magic # 0xc486a1e7 for agi 24
bad version # 127171049 for agi 24
bad sequence # 606867126 for agi 24
bad length # -48052605 for agi 24, should be 11446496
would reset bad sb for ag 24
would reset bad agi for ag 24
bad uncorrected agheader 24, skipping ag...
- 10:49:34: scanning filesystem freespace - 30 of 32 allocation
groups done
- found root inode chunk
Phase 3 - for each AG...
- scan (but don't clear) agi unlinked lists...
error following ag 24 unlinked list
- 10:49:34: scanning agi unlinked lists - 32 of 32 allocation
groups done
- process known inodes and perform inode discovery...
- agno = 0
- agno = 1
- agno = 2
- agno = 3
- agno = 4
imap claims a free inode 268435719 is in use, would correct imap and clear inode
bad nblocks 23 for inode 268435723, would reset to 13
corrupt block 0 in directory inode 259
would junk block
no . entry for directory 259
no .. entry for directory 259
- agno = 5
- agno = 6
- agno = 7
- agno = 8
attribute entry 0 in attr block 0, inode 2147610149 has bad name (namelen = 0)
problem with attribute contents in inode 2147610149
would clear attr fork
bad nblocks 11 for inode 2147610149, would reset to 10
bad anextents 1 for inode 2147610149, would reset to 0
attribute entry 0 in attr block 0, inode 2147610376 has bad name (namelen = 0)
problem with attribute contents in inode 2147610376
would clear attr fork
bad nblocks 13 for inode 2147610376, would reset to 12
bad anextents 1 for inode 2147610376, would reset to 0
- agno = 9
- agno = 10
- agno = 11
imap claims in-use inode 2173744652 is free, would correct imap
data fork in ino 2423071372 claims free block 201330859
data fork in ino 2423071372 claims free block 201330860
.....
would have reset inode 4090071559 nlinks from 5 to 3
would have reset inode 4130446080 nlinks from 6 to 4
would have reset inode 4130446132 nlinks from 5 to 4
would have reset inode 4130509338 nlinks from 21 to 19
would have reset inode 4136546816 nlinks from 5 to 4
would have reset inode 4136546819 nlinks from 5 to 4
would have reset inode 4136546822 nlinks from 5 to 4
would have reset inode 4136546825 nlinks from 5 to 4
would have reset inode 4168420144 nlinks from 7 to 4
- 10:54:24: verify link counts - 191040 of 202304 inodes done
No modify flag set, skipping filesystem flush and exiting.

Does dmesg have any info/sata errors?

xfs_repair will have problems if the disk is bad. You may want to image the disk (possibly onto the 'spare'?) if it is bad.

Very good idea :)

The order looks right to me.
xfs_repair wouldn't recognise it as well as it does if the order was wrong.

Bear in mind that -n stops the repair fixing a problem. Then as the 'repair' proceeds it becomes very confused by problems that should have been fixed.

This is evident in the superblock issue (which also probably explains the failed mount).

No the event count was very out of date.

Yes, there is some kind of media error message in dmesg, below. It is not random, it happens at exactly the same moments in each xfs_repair -n run.

Nov 11 09:48:25 altair kernel: [37043.300691]          res 51/40:00:01:00:00/00:00:00:00:00/e1 Emask 0x9 (media error)
Nov 11 09:48:25 altair kernel: [37043.304326] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:48:25 altair kernel: [37043.307672] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:48:25 altair kernel: [37043.307676] ata4.00: configured for UDMA/133
Nov 11 09:48:25 altair kernel: [37043.307684] ata4: EH complete
Nov 11 09:48:27 altair kernel: [37043.747838] SCSI device sdd: 976773168 512-byte hdwr sectors (500108 MB)
Nov 11 09:48:27 altair kernel: [37043.747861] sdd: Write Protect is off
Nov 11 09:48:27 altair kernel: [37043.747878] SCSI device sdd: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
Nov 11 09:49:19 altair kernel: [37065.709216]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:19 altair kernel: [37065.720197] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:19 altair kernel: [37065.732188] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:19 altair kernel: [37065.732192] ata4.00: configured for UDMA/133
Nov 11 09:49:19 altair kernel: [37065.732199] ata4: EH complete
Nov 11 09:49:21 altair kernel: [37067.206243]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:21 altair kernel: [37067.210721] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:21 altair kernel: [37067.215727] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:21 altair kernel: [37067.215731] ata4.00: configured for UDMA/133
Nov 11 09:49:21 altair kernel: [37067.215738] ata4: EH complete
Nov 11 09:49:24 altair kernel: [37068.107825]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:24 altair kernel: [37068.112730] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:24 altair kernel: [37068.117732] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:24 altair kernel: [37068.117736] ata4.00: configured for UDMA/133
Nov 11 09:49:24 altair kernel: [37068.117740] ata4: EH complete
Nov 11 09:49:26 altair kernel: [37069.095665]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:26 altair kernel: [37069.100156] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:26 altair kernel: [37069.105148] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:26 altair kernel: [37069.105152] ata4.00: configured for UDMA/133
Nov 11 09:49:26 altair kernel: [37069.105159] ata4: EH complete
Nov 11 09:49:28 altair kernel: [37069.996842]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:28 altair kernel: [37070.000912] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:28 altair kernel: [37070.005916] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:28 altair kernel: [37070.005919] ata4.00: configured for UDMA/133
Nov 11 09:49:28 altair kernel: [37070.005924] ata4: EH complete
Nov 11 09:49:31 altair kernel: [37070.983850]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:31 altair kernel: [37070.987914] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:31 altair kernel: [37070.992917] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:31 altair kernel: [37070.992920] ata4.00: configured for UDMA/133
Nov 11 09:49:31 altair kernel: [37070.992935] ata4: EH complete
Nov 11 09:49:31 altair kernel: [37071.000639] SCSI device sdd: 976773168 512-byte hdwr sectors (500108 MB)
Nov 11 09:49:31 altair kernel: [37071.000719] sdd: Write Protect is off
Nov 11 09:49:31 altair kernel: [37071.000745] SCSI device sdd: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
Nov 11 09:49:31 altair kernel: [37071.000762] SCSI device sdd: 976773168 512-byte hdwr sectors (500108 MB)
Nov 11 09:49:31 altair kernel: [37071.000770] sdd: Write Protect is off
Nov 11 09:49:31 altair kernel: [37071.000788] SCSI device sdd: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
Nov 11 09:49:33 altair kernel: [37072.213749]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:33 altair kernel: [37072.218227] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:33 altair kernel: [37072.223231] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:33 altair kernel: [37072.223235] ata4.00: configured for UDMA/133
Nov 11 09:49:33 altair kernel: [37072.223242] ata4: EH complete
Nov 11 09:49:36 altair kernel: [37073.283239]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:36 altair kernel: [37073.286894] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:36 altair kernel: [37073.290220] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:36 altair kernel: [37073.290224] ata4.00: configured for UDMA/133
Nov 11 09:49:36 altair kernel: [37073.290231] ata4: EH complete
Nov 11 09:49:38 altair kernel: [37074.094417]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:38 altair kernel: [37074.097652] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:38 altair kernel: [37074.100988] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:38 altair kernel: [37074.100992] ata4.00: configured for UDMA/133
Nov 11 09:49:38 altair kernel: [37074.100997] ata4: EH complete
Nov 11 09:49:40 altair kernel: [37074.992267]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:40 altair kernel: [37074.996747] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:40 altair kernel: [37075.000074] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:40 altair kernel: [37075.000078] ata4.00: configured for UDMA/133
Nov 11 09:49:40 altair kernel: [37075.000083] ata4: EH complete
Nov 11 09:49:42 altair kernel: [37075.803457]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:42 altair kernel: [37075.807516] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:42 altair kernel: [37075.810842] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:42 altair kernel: [37075.810846] ata4.00: configured for UDMA/133
Nov 11 09:49:42 altair kernel: [37075.810853] ata4: EH complete
Nov 11 09:49:44 altair kernel: [37076.700452]          res 51/40:00:0f:00:00/00:00:00:00:00/ef Emask 0x9 (media error)
Nov 11 09:49:44 altair kernel: [37076.704947] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:44 altair kernel: [37076.708272] ata4.00: ata_hpa_resize 1: sectors = 976773168, hpa_sectors = 976773168
Nov 11 09:49:44 altair kernel: [37076.708275] ata4.00: configured for UDMA/133
Nov 11 09:49:44 altair kernel: [37076.708290] ata4: EH complete
Nov 11 09:49:44 altair kernel: [37076.709550] SCSI device sdd: 976773168 512-byte hdwr sectors (500108 MB)
Nov 11 09:49:44 altair kernel: [37076.709572] sdd: Write Protect is off
Nov 11 09:49:44 altair kernel: [37076.709594] SCSI device sdd: write cache: enabled, read cache: enabled, doesn't support DPO or FUA
Nov 11 09:49:44 altair kernel: [37076.709611] SCSI device sdd: 976773168 512-byte hdwr sectors (500108 MB)
Nov 11 09:49:44 altair kernel: [37076.709623] sdd: Write Protect is off
Nov 11 09:49:44 altair kernel: [37076.709705] SCSI device sdd: write cache: enabled, read cache: enabled, doesn't support DPO or FUA

I'm not sure what an ata_hpa_resize error is...

It probably explains the problems you've been having with the raid not 'just recovering' though.

I saw this:
http://www.linuxquestions.org/questions/linux-kernel-70/sata-issues-568894/

What does smartctl say about your drive?

IMO the spare drive is no longer useful for data recovery - you may want to use ddrescue to try and copy this drive to the spare drive.

David
PS Don't get the ddrescue parameters the wrong way round if you go that route...

HPA = Hardware Protected Area.

By any chance is this disk partitioned such that the partition size includes the HPA? If it does, this sounds at least familiar, this mailing list post may get you started: http://osdir.com/ml/linux.ataraid/2005-09/msg00002.html

In any case, run "fdisk -l" and look at the claimed total disk size and the end point of the last partition. The HPA is not included in the "disk size" so nothing should be trying to do so.

May be the same thing. Let us know what fdisk reports.

bill davidsen <[email protected]>
 CTO TMR Associates, Inc
 Doing interesting things with small computers since 1979

Yes, this is exactly the kind of symptoms I've experienced. I was losing a drive here and there every couple of months (mostly the last two drives sdc and sdd) which I though were cable problems (shut down, re-plug the cables and restart and it would always work, with add/rebuild the 4th disk). But now my guess is the motherboard chipset is overheating (or maybe the drives). I have an MSI K9N platinum AMD/Nividia chipset that has 4 raid ports + 2 raid ports from a separate chip. The mb chipset comes with a wimpy heatsink on it and it is very hot to the touch. I had been planning to replace it but never got around to it.

I've been out of town this week so I had someone image all three disks. He used ghost disk image application. He said the third disk reported media problems, and about 5% of the data was not fixable (sector errors). Using these three copied drives, the array comes up and xfs_repair still reports a bunch of inode repairs as before, but it is a bit different, maybe even a reduction in losses. But most important is the hpa_sector errors no longer occur.

Key questions:
- I assume ddrescue will do a much better job of correcting errors when imaging a disk? My colleague used ghost which is just a copy tool. I don't understand the capabilities of ddrescue on raid partitions that well.
- fdisk -l reports that all the drives are exactly the same size with exactly the same # sectors shown below. I don't quite follow the hpa_resize issue, but it appears the drives don't have hidden HPA sectors - I guess? Note that sdc is the original drive, where sda, sdb, and sdd are the imaged drives.

So what do you recommend to do first? Should I try xfs_repair on the ghost copy, or just re-copy myself using ddrescue? Are there special settings to ddrescue I should consider to verify/correct potential HPA changes?

Thks,
Chris

Disk /dev/sda: 500.1 GB, 500107862016 bytes
/dev/sda1 1 60801 488384001 fd Linux raid autodetect
Disk /dev/sdb: 500.1 GB, 500107862016 bytes
/dev/sdb1 1 60801 488384001 fd Linux raid autodetect
Disk /dev/sdc: 500.1 GB, 500107862016 bytes
/dev/sdc1 1 60801 488384001 fd Linux raid autodetect
Disk /dev/sdd: 500.1 GB, 500107862016 bytes
/dev/sdd1 1 60801 488384001 fd Linux raid autodetect

ddrescue should do a *much* better job.
It knows nothing about raid and operates on the underlying device. It retries bad sectors in a clever manner.

No
or just re-copy myself using ddrescue?
Yes.
Are there special

Ideally just ddrescue the entire device to a file and use loopback.

For the faulty disk then if you have space, make a second copy and xfs_repair using that. If it fails then you can easily re-image the good disks but it may not be so easy to re-image the bad one.

David