[one-users] Oned failover mechanism and multi-cluster deployment ?

[Ignacio M. Llorente]

Hi

You can group physical hosts in clusters with different levels of
security or with different hardware devices (AFAIK these two are the
more typical scenarios). For example you could have two different
clusters, one with a low latency/high bandwidth network for tightly
coupled services (a computing cluster to execute HPC MPI applications)
and another with a higher latency for loosely coupled services (a
computing cluster to execute HTC multi-task applications). Users can
then use the requirements attribute to define the suitable cluster for
their workload.

Regards

On Fri, Nov 12, 2010 at 7:57 PM, Steven Timm <timm at fnal.gov> wrote:
> I have seen the new feature about logical clusters
> (the onecluster command) but it wasn't clear what
> capacities it really brings.  Is there any benefit to
> defining more than one cluster with the onecluster command,
> if so, what?
>
> Steve
>
>
> On Fri, 12 Nov 2010, Tino Vazquez wrote:
>
>> Hi Ivan,
>>
>> We are currently working on different levels of fault tolerance. We
>> want to have (in the short term) a best practices document to achieve
>> fault tolerance with OpenNebula.
>>
>> About a multi-cluster deployment architecture, there is currently two
>> ways of achieving this:
>>
>> * Logic clusters: this is a new feature introduced in the 2.0 version.
>> See [1] for details.
>> * Federation can be achieved using plugins, where for instance the
>> Amazon EC2 driver and server is used to federate different clusters,
>> each one of them managed by one OpenNebula instance.
>>
>> Hope it helps,
>>
>> -Tino
>>
>> --
>> Constantino Vázquez Blanco | dsa-research.org/tinova
>> Virtualization Technology Engineer / Researcher
>> OpenNebula Toolkit | opennebula.org
>>
>>
>>
>> On Mon, Oct 25, 2010 at 2:17 PM, Ivan Frain <ivan.frain at gmail.com> wrote:
>>>
>>> Hi everybody,
>>>
>>> I would like to know if there is a failover mechanism for oned ? I'am
>>> sure
>>> that it is possible to manage this failover using MySQL as database
>>> backend
>>> on a remote server but I would like to have more details: should we use
>>> active/standby mechanism with heartbeat, is there any guidelines to do
>>> this
>>> ...
>>> Moreover, in the case of oned failure, what are the guarantees about its
>>> state and the recovery?
>>> I didn't find any documentation in the OpenNebula web site this is why I
>>> post my question here.
>>>
>>> I have another question concerning a multi cluster management. I
>>> understand
>>> the deployment of opennebula in one cluster with one frontend node on
>>> which
>>> 'oned' is installed but what could be a deployment with several physical
>>> clusters cooperating each one running opennebula toolkit? Can we put in
>>> place a kind of hierarchy like Eucalyptus: cloud controller, cluster
>>> controller and so on ?
>>>
>>> Thank you in advance.
>>> Best regards,
>>> --
>>> Ivan Frain
>>>
>>>
>>>
>>>
>>> _______________________________________________
>>> Users mailing list
>>> Users at lists.opennebula.org
>>> http://lists.opennebula.org/listinfo.cgi/users-opennebula.org
>>>
>>>
>> _______________________________________________
>> Users mailing list
>> Users at lists.opennebula.org
>> http://lists.opennebula.org/listinfo.cgi/users-opennebula.org
>>
>
> --
> ------------------------------------------------------------------
> Steven C. Timm, Ph.D  (630) 840-8525
> timm at fnal.gov  http://home.fnal.gov/~timm/
> Fermilab Computing Division, Scientific Computing Facilities,
> Grid Facilities Department, FermiGrid Services Group, Assistant Group
> Leader.
>
>
> _______________________________________________
> Users mailing list
> Users at lists.opennebula.org
> http://lists.opennebula.org/listinfo.cgi/users-opennebula.org
>
>



-- 
Ignacio M. Llorente, Full Professor (Catedratico):
http://dsa-research.org/llorente
DSA Research Group:  web http://dsa-research.org and blog
http://blog.dsa-research.org
OpenNebula Open Source Toolkit for Cloud Computing: http://www.OpenNebula.org