Makes sense it's not as fast, and what Andrew said is what I was looking for. 
Space is an issue at times, and using virtualization with xen hypervisor is
a reasonable solution, this is especially true when experimenting with HBase
and data modeling.  My point here was to find specifics on optimal cluster
setup for running Hadoop/HBase in the real world, since I'm not yet that
familiar with the internals of these systems.  We had an existing box, and
setup VMs, since it was an easy way to go at the time, we are still in early
stages and attempting to determine if HBase is a feasible solution.  Moving
to production, if we do, will likely require rethinking the setup, and that
was the primary reason for my request for clarification (on why VM = low
performance) here, so people who have been working in a cluster environment
can weigh in.  

Thanks.


Ryan Rawson wrote:
> 
> Why do I think VM is low performance?  I could ask you, why do you
> think that Virtualizing is as fast as native?
> 
> 
> On Wed, Aug 19, 2009 at 2:33 PM, llpind<[email protected]> wrote:
>>
>>
>> Ryan Rawson wrote:
>>>
>>> Absolutely not.  VM = low performance, no good.
>>>
>>
>> If you have a box with a lot of RAM, and you split the box into VMs
>> allocating enough RAM for each.
>>
>> Lets say you have a box with 32GB of RAM, and you put two VMs on it
>> allocating 16GB each... will that be slow too?
>>
>> please explain why you think VM = low performance.  thanks
>> --
>> View this message in context:
>> http://www.nabble.com/HBase-in-a-real-world-application-tp24920888p25052355.html
>> Sent from the HBase User mailing list archive at Nabble.com.
>>
>>
> 
> 

-- 
View this message in context: 
http://www.nabble.com/HBase-in-a-real-world-application-tp24920888p25119754.html
Sent from the HBase User mailing list archive at Nabble.com.

Reply via email to