[rabbitmq-discuss] another performance question

Wed Jul 17 22:37:01 BST 2013

Matthias,

One last attempt at reproducing your results. I found a newer server, Dell R610, and ran the same test and got the same results as you see. So my poor performance can at least partially be accounted for with the old machine I was using. Also, I think we will re-think the use of a VM for hosting brokers since that also made a significant difference. The VM I tested on was running on a Dell R710 so should be somewhat better than the R610.

So I assume that we can only expect to achieve about the 50kHz number with no consumers, or bindings then.

Mark Geib
Principal Engineer
Cheyenne Software Engineering
mark.geib at echostar.com / 35-215

“We, the unwilling, led by the unknowing, are doing the impossible for the ungrateful. We have done so much, for so long, with so little, we are now qualified to do anything with nothing.” 
― Mother Teresa

On Jul 17, 2013, at 2:05 PM, Matthias Radestock wrote:

> On 17/07/13 21:00, Geib, Mark wrote:
>> No, my initial reply to you was output on a bare metal. The VM
>> results were just to confirm our performance numbers.
>> 
>> My main testing machine is bare metal.
> 
> I have no idea then what could be the cause. Try running with an R16B compiled from source, since that's what I'm running. I doubt it will make a difference, but I can't think of anything else to try.
> 
> Matthias.
> 