Gluster users - Oct 2012 - Block replication with glusterfs for NFS failover

Hi,

to enable NFS state transfer between hosts in a failover SAN, it is 
necessary to have the NFS state data on the exact same blocks on both 
storage nodes:
http://serverfault.com/a/274995 
<http://serverfault.com/questions/274990/fault-tolerant-nfs/274995#274995>
http://sysconfig.org.uk/2011/07/glusterfs-a-workhorse-that-needs-to-be-tamed/

"You MUST have a shared (precisely the same block for block) filesystem 
or NFS failover won't work, and you'll get stale NFS file handles."
http://lists.linux-ha.org/pipermail/linux-ha/2004-September/012005.html

Simply linking /usr/lib/nfs to the glusterfs volume doesn't work.

My questions:
Can I somehow enable block-for-block replication with GlusterFS?
What is this: 
http://gluster.org/community/documentation/index.php/Gluster_3.2:_Provisioning_Storage_on_Gluster_Virtual_Storage_Appliance

Thank you.

--
Best Regards
Runar Ingebrigtsen
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://supercolony.gluster.org/pipermail/gluster-users/attachments/20121023/bf804afd/attachment.html>

On Tue, Oct 23, 2012 at 01:55:01PM +0200, Runar Ingebrigtsen
wrote:
>    to enable NFS state transfer between hosts in a failover SAN, it is
>    necessary to have the NFS state data on the exact same blocks on both
>    storage nodes:
You are reading a document for something which is not glusterfs.
>    Can I somehow enable block-for-block replication with GlusterFS?
No. You are reading documentation for something completely different: a pair
of machines synchronised at the block level using DRBD, in a master/slave
configuration (that is: all writes must be made on the master side, and the
block changes are replicated a la RAID1 but over a network).

I suggest you ask a different question: "can I have failover between two
gluster NFS servers without getting stale filehandles?"

I don't know the answer to that myself, but I have seen messages which
suggests others may have it working:
http://gluster.org/pipermail/gluster-users/2012-June/010700.html