Open Stack

Hi Ray

the measurement is quite interesting. but I suppose the performance is not
because of openstack but it may be factored by rabbimq itself.

On the other hand, I would like to know which version of rabbitmq you are
using ?

Thanks,
Dan

On 20 November 2012 16:05, Ray Pekowski <pekowski at gmail.com> wrote:

> Andrea,
>
> On Mon, Nov 19, 2012 at 5:55 AM, Rosa, Andrea (HP Cloud Services) <
> andrea.rosa at hp.com> wrote:
>
>>  Hi Ray****
>>
>> ** **
>>
>> What about discussing your results with rabbimq team (through the
>> rabbimtq mailing list)?****
>>
>> Maybe we are missing something.
>>
>
> Thanks for the suggestion, I will pursue the RabbitMQ queue/exchange
> replication serialization with the RabbitMQ team and in parallel develop
> the code to remove the dynamic creation of queues and exchanges.  I have an
> initial prototype that shows promise.  It is a huge improvement to
> throughput even in the non-clustered case and initial measurements show
> that it doesn't exhibit the serialization problem in the clustered case.
> I'm firming up the measurements now.
>
> Vish says this should be done in oslo-incubator.  Can someone point me to
> the process?  Should I start with a blueprint?
>
> Ray
>
> _______________________________________________
> OpenStack-dev mailing list
> OpenStack-dev at lists.openstack.org
> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev
>
>


-- 
Dan He
-----------------------
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack-dev/attachments/20121120/d76a0c26/attachment.html>