3

Once in a while, we encounter input/output errors on one of our disks.

Our server (DELL PowerEdge R720, Ubuntu 14.04) uses the Perc H710 Raid controller, and the disk that is producing the error is a Dell 600GB SAS 6Gbps 15k 3.5" disk.

We can always fix the errors, using fsck.ext4, but we have no idea what might cause them to occur.

We've updated the server firmware to the latest version, and ran all of the tests we could think of.

What else could we do to find the source of the problem?

EDIT:

We have contacted DELL about a week ago, and after they instructed me how to run several tests, they concluded that the server is fine, and that nothing unusual showed up in the tests.

I couldn't enable SMART support for the device:

$ sudo smartctl -a /dev/sda
smartctl 6.2 2013-07-26 r3841 [x86_64-linux-3.13.0-55-generic] (local build)
Copyright (C) 2002-13, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Vendor:               DELL
Product:              PERC H710
Revision:             3.13
User Capacity:        1,199,101,181,952 bytes [1.19 TB]
Logical block size:   512 bytes
Logical Unit id:      0x6b8ca3a0f210dc0019eead8c1111fb0a
Serial number:        000afb11118cadee1900dc10f2a0a38c
Device type:          disk
Local Time is:        Wed Jul  8 10:47:35 2015 IDT
SMART support is:     Unavailable - device lacks SMART capability.

=== START OF READ SMART DATA SECTION ===

Error Counter logging not supported

Device does not support Self Test logging

and i tried:

$ sudo smartctl -s on /dev/sda
smartctl 6.2 2013-07-26 r3841 [x86_64-linux-3.13.0-55-generic] (local build)
Copyright (C) 2002-13, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF ENABLE/DISABLE COMMANDS SECTION ===
unable to fetch IEC (SMART) mode page [unsupported field in scsi command]
A mandatory SMART command failed: exiting. To continue, add one or more '-T permissive' options.

Also, i'm not sure what to make of this (googling didn't help):

$ sudo hdparm -I /dev/sda

/dev/sda:
SG_IO: bad/missing sense data, sb[]:  70 00 05 00 00 00 00 0d 00 00 00 00 20 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

ATA device, with non-removable media
Standards:
    Likely used: 1
Configuration:
    Logical     max current
    cylinders   0   0
    heads       0   0
    sectors/track   0   0
    --
    Logical/Physical Sector size:           512 bytes
    device size with M = 1024*1024:           0 MBytes
    device size with M = 1000*1000:           0 MBytes 
    cache/buffer size  = unknown
Capabilities:
    IORDY not likely
    Cannot perform double-word IO
    R/W multiple sector transfer: not supported
    DMA: not supported
    PIO: pio0 

Any advice is most welcomed !

4
  • 1
    You should describe in more detail exactly what tests "all the tests you could think of" actually were
    – noitsbecky
    Jul 7, 2015 at 12:09
  • 1
    make sure you check the SMART values, most likely you already see an issue there. Jul 7, 2015 at 12:49
  • Thanks, i've updated my answer. hope it provides sufficient information.
    – R. Itzi
    Jul 8, 2015 at 9:52
  • Have you tested ALL of the drives? Are the results for the "iffy" drive exactly the same as the others in the RAID? If not, how are they different? Jul 10, 2015 at 10:56

3 Answers 3

8

You have one drive in a RAID that is misbehaving, and producing occasional errors? Sounds like a hardware problem, and one that is likely to get worse. You should consider replacing the drive. Yes, it's expensive, but how much is your time worth, and how bad would it be if the entire drive went south at an inopportune moment?

3

Can you see the SMART information for the individual disks via the Disk Utility? Look at the Pre-Fail checks & see if anything stands out. This will indicate a failing physical device.

Is the disk that's producing the errors in a RAID group with other disks? If not it may be the file system and not the drive or, depending on the layout, could be the controller (bad cache, firmware mismatch). I would also check the firmware versions on the disk & controller to see if they are woefully out of date.

Do you have other disks of the same type on this controller? Do they have the same firmware etc?

1
  • Thanks ! I've updated my question. With regards to your questions: I can't get SMART to work (the updated question contains the details), the disk that is producing the errors is indeed in a RAID group with other disks.
    – R. Itzi
    Jul 8, 2015 at 9:53
0

What specific errors are you receiving?

I would recommend trying to get some more information from the PERC controller. With Ubuntu, you may not be able to install Dell's OMSA for monitoring and management.

You could likely install MegaCLI and use it to export a controller log to get more info on events that are occurring.

Is there a reason you haven't contacted Dell support? That server model seems new enough I'd expect it to still be under warranty...

1
  • The errors i get are "Input/output error" when using ls, tar or any other command that tries to access those files. I'm still trying to install MegaCLI on our Ubuntu 14.04.
    – R. Itzi
    Jul 8, 2015 at 8:48

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .