[Gluster-devel] Re: Strange behavior of AFR

gordan at bobich.net gordan at bobich.net
Wed May 21 15:36:53 UTC 2008


On Wed, 21 May 2008, Anton Khalikov wrote:

>> This may be to do with tthe posix locking. Currently posix lock server is
>> the first server in the AFR list (and the order of servers in AFR whould
>> be the same on all nodes, or else the locking won't work properly). When
>> the primary (lock) server goes away, all the locks disappear, too. There
>> was also another thread there discussing lock / metadata distribution
>> across the cluster with quorum locking. But that is also as yet
>> unimplemented.
>
> Do you mean posix-locks translator or what ? I don't use it by the way.

Yes. If you're not using it, then it can't be the underlying cause.

>> If it's timeout related, then yes, head-ing the images will solve the
>> problem. If it's lock related, it won't make any difference.
>
> Yes it is timeout related. XEN tools as well as domU kernels try to
> reach filesystem and their requests are blocked until resync is 100%
> complete. It raises timeouts.

In that case, doing head -1 on the files in question before migrating the 
VM back should solve the problem.

Gordan





More information about the Gluster-devel mailing list