Re: 2-node RAC faster than 6-node!

From: Dan Norris <dannorris_at_dannorris.com>
Date: Thu, 03 Apr 2008 13:45:13 -0500
Message-ID: <47F525B9.7030602@dannorris.com>


Yong,

I suppose that there may be some difference between 4 and 6 nodes with respect to the occurrence of 2 vs 3-way block negotiations. However, I don't think that will be a noticeable. I think the only time you'd have enough impact to really measure the difference would be between 2 and 3 nodes and that's supported by the study I mentioned (that I still can't seem to locate).

Dan

Yong Huang wrote:

> Dan's theory says in case of 6 nodes,
> there's relatively more 3-way traffic, which could slow down the overall
> performance. Correct, Dan?
>   

>> From: Dan Norris <dannorris_at_dannorris.com>
>>
>> ... In any case where a
>> block is cached in another instance, there are three parties involved: the
>> requestor, the holder, and the global resource master for the requested
>> block. In a two-node cluster, two of these three parties are the same
>> instance and therefore the messaging between them is very fast. When a third
>> node is added, there's a statistical probability that these three parties
>> will involve all three instances for a significant portion of the
>> occurrencesof this situation. In the case where three instances are
>> involved,the communications take longer since all messaging has to cross the
>> interconnect.
>>
--
http://www.freelists.org/webpage/oracle-l
Received on Thu Apr 03 2008 - 13:45:13 CDT

Original text of this message