[CentOS] errors in logs - kernel: XFS (dm-7): xlog_space_left: head behind tail

[Gregory Machin]

On Wed, Mar 21, 2012 at 11:13 AM, John R Pierce <pierce at hogranch.com> wrote:
> On 03/20/12 2:54 PM, Gregory Machin wrote:
>> I have a CentOS 6.2 virtual machine in a vmware ESXi 4.0 host 4G Ram 4
>> virtaul cpus and with about 4 TB of disk space formatted with XFS .
>> I'm seeing a lot of :
>>
>> Mar 21 10:49:42 nzhmlfpr05 kernel: XFS (dm-4): xlog_space_left: head behind tail
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  tail_cycle = 129, tail_bytes = 20163072
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  GH   cycle = 129, GH   bytes = 20162880
>> Mar 21 10:49:42 nzhmlfpr05 kernel: XFS (dm-7): xlog_space_left: head behind tail
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  tail_cycle = 5, tail_bytes = 333417984
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  GH   cycle = 5, GH   bytes = 333417792
>> Mar 21 10:49:42 nzhmlfpr05 kernel: XFS (dm-7): xlog_space_left: head behind tail
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  tail_cycle = 5, tail_bytes = 333417984
>> Mar 21 10:49:42 nzhmlfpr05 kernel:  GH   cycle = 5, GH   bytes = 333417792
>>
>> What would casue this ? A quick google , I found a post that indicated
>> I should unmount and mount the file systems. I have live production
>> data on this machine so I need to be careful. What is the best
>> solution ?
>
> what sort of physical disk storage is this vm using?   I'm wondering if
> perhaps this storage is unreliable with regards to write commits, or
> write ordering.
>

> --
> john r pierce                            N 37, W 122
> santa cruz ca                         mid-left coast

Hi John

The ESX host is attache to an Infortrend iSCSI SAN with 2 RAID5 arrays
, each array has 3 LUNs. The disk are 7200 SATA Seagate disks.The
virtual machines run out off disks the reside on the LUNs..

I will have a look at the SAN and see if there are any errors.

Thanks