[Lustre-discuss] mounting Failover OSTs

[Wojciech Turek]

Hi Andrus,

Lustre does not fully support failover. It only allows to configure OST so
it can be accessed on more then one OSS. However handling a failure and
operation of mounting device on the failover OSS is not automatically  done
by Lustre. You can not mount OST on both OSS servers simultaneously that
would cause a corruption of the ldiskfs filesystem. Fortunately since some
time ldiskfs comes with mmp (multi mount protection) flag which will stop
you doing that (and this is probably what you are seeing in the logs). As
Jeff says to fully automatically configure failover in lustre you will need
to use additional HA software like  Heartbeat with Pacemaker or Corosync
with Pacemaker. There are others as well but these two are most popular I
think.

Best regards,

Wojciech

On 11 October 2012 22:02, Andrus, Brian Contractor <bdandrus at nps.edu> wrote:

> All,
>
> I am starting to try and configure failover for our lustre filesystem.
> Node00 is the mgs/mdt
> Node00 is the oss for ost0 and failnode for ost1
> Node01 is the oss for ost1 and failnode for ost0
>
> Both osts are on an SRP network and are visible by both nodes.
> Ost0 is mounted on node00
> Ost1 is mounted on node01
>
> If I try to mount ost0 on node01 I see in the logs for node00:
>         kernel: Lustre: Denying initial registration attempt from nid
> 10.100.255.250 at o2ib, specified as failover
>
> So do I have to manually mount the ost for failover purposes when there is
> a fail?
> I would have thought I mount the osts on both nodes and lustre will manage
> which node is the active node.
>
>
> Brian Andrus
> _______________________________________________
> Lustre-discuss mailing list
> Lustre-discuss at lists.lustre.org
> http://lists.lustre.org/mailman/listinfo/lustre-discuss
>



-- 
Wojciech Turek

Senior System Architect

High Performance Computing Service
University of Cambridge
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20121012/3081c742/attachment.htm>